Security

Cloudflare Radar API

Free internet intelligence API from Cloudflare providing global traffic trends, BGP routing data, DNS query statistics, attack trends, and internet quality metrics aggregated from Cloudflare's global network.

CrowdStrike Falcon

Cloud-native endpoint detection and response (EDR/XDR) platform that protects devices against malware and advanced threats, with a REST API and MCP server for security automation and threat hunting.

Snyk API

Snyk's REST API provides programmatic access to developer security scanning results across four product lines: Snyk Open Source (dependency vulnerability scanning across npm, PyPI, Maven, Go, Ruby, and 20+ ecosystems), Snyk Code (AI-powered SAST for first-party code), Snyk Container (container image and Dockerfile scanning), and Snyk IaC (Terraform, Kubernetes, CloudFormation security). The API enables querying findings, managing projects, triggering scans, and integrating security data into CI/CD pipelines, SOAR workflows, and security dashboards. Snyk maintains one of the largest proprietary vulnerability databases, often providing fix guidance and prioritization intelligence beyond raw CVE data.

Let's Encrypt (ACME)

Free, automated certificate authority that issues TLS/SSL certificates via the ACME protocol, enabling agents and automation to programmatically obtain, renew, and revoke certificates without manual intervention.

Have I Been Pwned API

API for checking whether email addresses, usernames, or passwords have appeared in known data breaches, built and maintained by Troy Hunt. Covers billions of breached credentials.

Semgrep API

Semgrep is a fast, open-source static analysis engine with a cloud platform (Semgrep AppSec Platform) for managing findings across codebases at scale. The REST API provides programmatic access to scan findings, project management, deployment configuration, and supply chain vulnerability data. Semgrep's rule language enables custom pattern matching without complex ASTs, making it popular for both security research and DevSecOps automation. The API is the automation layer for teams running Semgrep in CI/CD and wanting to build custom triage, reporting, or remediation workflows.

AbuseIPDB API

Crowdsourced IP address reputation database for checking and reporting abusive IPs. Aggregates abuse reports from thousands of contributors for spam, DDoS, brute force, and malicious activity.

GhidrAssistMCP

A Ghidra extension that implements a full MCP server, exposing 34 analysis tools, 5 resources, and 5 prompts for AI-assisted reverse engineering. Enables external AI tools to interact with Ghidra's decompiler, disassembler, and analysis capabilities over HTTP (SSE and Streamable transports).

VirusTotal API

Aggregates antivirus scan results from 70+ engines for files, URLs, domains, and IP addresses. Provides threat intelligence, behavioral analysis, and community-driven reputation data.

Socket Security API

Socket Security provides deep package analysis for open-source dependencies across npm, PyPI, Maven, Conda, and other ecosystems, detecting supply chain attacks, malware, typosquatting, protestware, and risky code patterns before they enter your codebase. Unlike CVE-only scanners, Socket analyzes the actual package code for suspicious behaviors like unexpected network calls, shell execution, filesystem access, and obfuscated code — catching zero-day supply chain threats that CVE databases miss. The REST API enables programmatic package scoring, CI/CD integration, and alert management.

IDA Pro MCP

MCP server that exposes IDA Pro's reverse engineering capabilities to AI agents. Enables decompilation, disassembly, xref analysis, function renaming, commenting, patching, debugger control, and arbitrary IDAPython execution through MCP tools.

Wiz

Agentless cloud security platform that scans cloud environments for vulnerabilities, misconfigurations, and attack paths using a graph-based security model, with a GraphQL API for querying risk data.

ReVa (Reverse Engineering Assistant)

Ghidra extension that implements an MCP server, enabling AI language models to perform reverse engineering tasks like decompilation, symbol renaming, encryption detection, and binary analysis directly through Ghidra's analysis engine.

Lacework

Cloud security platform using machine learning for anomaly-based threat detection, cloud posture management, and vulnerability assessment across cloud and Kubernetes environments, with a REST API for automation.

avakill

AvaKill is an open-source safety “firewall” for AI agents: it intercepts tool calls, evaluates them against a YAML policy (deny-by-default, rule-based checks including shell/path/content scanning, rate limits, and approval gates), and blocks/kills dangerous operations before execution. It provides multiple enforcement paths: native agent hooks, an MCP proxy/wrapper, and OS-level sandboxing, with an optional daemon for shared evaluation and audit logging.

MCP Gateway

A plugin-based MCP gateway that sits between an LLM and other MCP servers, intercepting and sanitizing requests/responses to prevent PII leakage, token/secret exposure, prompt injection attacks, and harmful content — with built-in security scanning of MCP server reputation.

oracle.oci-vault-key-management-mcp-server

Provides MCP server integration for managing keys within Oracle Cloud Infrastructure Vault.

Shodan API

Search engine for internet-connected devices, providing data on open ports, running services, software versions, vulnerabilities (CVEs), and geolocation for any IP or domain.

Aderyn

Aderyn is a Rust-based static analyzer built specifically for Solidity smart contracts, developed by Cyfrin (a leading smart contract security audit firm). It compiles and analyzes the AST of Solidity contracts to detect vulnerability patterns including reentrancy, unchecked return values, weak randomness, centralization risks, and dozens of other known vulnerability classes. Unlike general-purpose linters, Aderyn understands Solidity semantics deeply — including storage layout, function visibility, and call graph analysis. It supports Foundry and Hardhat project layouts with zero configuration, outputting reports in Markdown, JSON, or SARIF for CI/CD integration. The tool also exposes an MCP server interface (tagged in GitHub topics, though minimally documented) enabling AI agents to invoke contract analysis directly.

shodan-mcp

shodan-mcp is an MCP (Model Context Protocol) server that exposes Shodan capabilities as 20 callable tools for AI agents. It supports passive reconnaissance and vulnerability intelligence (CVE/CPE) and provides 4 tools that work without a Shodan API key.

oracle.oci-scanning-mcp-server

MCP server providing Oracle Cloud Infrastructure (OCI) scanning capabilities for vulnerability detection, security assessment, and compliance checking of OCI resources

oracle.oci-threat-intelligence-mcp-server

MCP server that provides programmatic access to Oracle Cloud Infrastructure Threat Intelligence services, enabling agents to query threat data, indicators of compromise, and security intelligence from OCI's threat intelligence platform.

caido-mcp-server

Provides an MCP server (stdio) and a CLI that let AI assistants or a terminal browse, replay, and analyze HTTP traffic through a local Caido proxy. Includes tools for proxy history queries, replaying requests, inspecting automate/fuzzing sessions, creating/listing security findings, and managing scopes/projects/workflows/intercept status.

JADX AI MCP

JADX decompiler plugin that exposes 28 MCP tools for AI-assisted Android APK reverse engineering. Enables LLMs to decompile, search, cross-reference, refactor, and analyze Android applications in real-time through the JADX GUI, including vulnerability detection, manifest analysis, resource inspection, and debugging integration.

MCP Security Hub

A collection of 36 Docker-based MCP servers developed by FuzzingLabs that expose 175+ offensive security tools (Nmap, Nuclei, SQLMap, radare2, Ghidra, Shodan, VirusTotal, OpenVAS, and more) to AI assistants via natural language for authorized penetration testing and security assessments. Each tool category runs in its own isolated Docker container, providing some process isolation between tool execution environments. Docker Compose orchestrates the full toolkit. The modular design allows deploying only the containers relevant to a specific engagement — binary analysis containers separately from web scanning containers, for example.

BloodHound MCP AI

An MCP server that bridges BloodHound's Active Directory attack path analysis database to AI assistants, exposing 75+ tools for querying AD attack paths, privilege escalation routes, Kerberos vulnerabilities (Kerberoasting, AS-REP roasting), NTLM relay opportunities, and Active Directory Certificate Services (ADCS) misconfigurations via natural language. Instead of writing Cypher graph traversal queries manually, security professionals can ask an AI 'show me all paths from a Domain User to Domain Admin' and get results from their BloodHound Neo4j database. Designed for authorized penetration testing engagements where BloodHound data has already been collected from target AD environments.

aguara

Aguara is a local security scanner (CLI + library + Docker) that statically analyzes AI agent skills and MCP server/tool configurations to detect issues such as prompt injection, data exfiltration, credential leaks, and supply-chain/persistence/rug-pull patterns. It supports decoded/obfuscated content scanning, cross-file taint/risk flow analysis within an MCP server directory, and produces terminal/JSON/SARIF/Markdown outputs suitable for CI.

toolbox

toolbox/sectool is a CLI + MCP server that enables collaborative application security testing between a human operator and an AI agent. It provides a wire-fidelity HTTP(S) MITM proxy (native, and optional Burp as a front-end), captures and replays authenticated browser/proxy traffic, supports crawling/diffing/reflection detection and out-of-band interaction testing (OAST via Interactsh), and exposes these capabilities as MCP tools (plus CLI commands sharing state).

slither-mcp

Provides an MCP (Model Context Protocol) server that wraps Slither static analysis to analyze Solidity projects and expose contract/function metadata and Slither detector results via MCP tools. Includes caching of Slither project facts and an optional typed Python client for tool invocation.

Agentic Radar

Agentic Radar is a security scanner by SPLX.ai that performs static analysis on agentic AI system codebases to identify vulnerabilities specific to AI workflows — prompt injection risks, PII leakage through tool outputs, insecure tool integrations, and over-privileged agent permissions. It supports multiple agent frameworks (OpenAI Agents SDK, CrewAI, LangGraph, n8n, AutoGen) and generates visual dependency graphs mapping the agent's tool and service exposure. The tool maps findings to OWASP LLM Top 10 categories and can run runtime adversarial prompt injection tests against live OpenAI Agents-based systems. It is designed to be run in CI/CD pipelines as a gate before deploying agentic systems to production.

atomic-red-team-mcp

Provides an MCP (Model Context Protocol) server that exposes Atomic Red Team test content and operations, including searching for “atomics,” refreshing/downloading atomic definitions, validating atomic YAML, retrieving a validation schema, and (optionally) executing atomic tests when explicitly enabled.

HexStrike AI

MCP server that enables AI agents to autonomously execute 150+ cybersecurity tools across network recon, web app testing, auth cracking, binary analysis, cloud security, and CTF/forensics. Features 12+ specialized AI agents for orchestrating complex security workflows.

pic-standard

PIC (Provenance & Intent Contracts) is a Python library/CLI and integration set that validates structured “action proposals” for AI agents, enforcing fail-closed checks on intent/impact, provenance trust, and evidence (hash/signature) before allowing tool execution.

agentseal

AgentSeal is a local-first security toolkit/CLI and Python/TypeScript library for auditing AI agent configurations and prompts. It scans for dangerous “skill”/agent files, checks MCP server/tool configurations for poisoning, analyzes toxic data flows, provides prompt red-teaming via adversarial probes, and can continuously watch/alert on changes to agent config files.

validation-mcp-server

validation-mcp-server is an offline, Python-based Model Context Protocol (MCP) server that provides Ethereum address/key validation and related cryptographic utilities (e.g., EIP-55 checksum validation, private-key range checking, checksummed conversion, signature component/value validation, hashing like keccak256, function selector encoding/decoding, ENS format validation, and storage-slot computation).

wazuh-mcp-server

Provides a Model Context Protocol (MCP) server that exposes Wazuh Manager and syscollector data (agents, ports, packages, processes, rules, rule files, and SCA results) as MCP tools, including an authentication tool to refresh JWT tokens used to call the Wazuh Manager API.

LitterBox

A controlled malware testing sandbox that enables red teams to develop and test payloads against detection systems. Provides static and dynamic analysis, YARA scanning, BYOVD detection, fuzzy hashing, and process behavior monitoring. Includes an MCP server (LitterBoxMCP) for LLM-driven malware analysis workflows.

okta-mcp-server

Provides an MCP (Model Context Protocol) server that lets LLMs/agents perform Okta admin management operations (CRUD on users, groups, apps, policies, etc.) by calling Okta’s Admin Management APIs. Supports interactive Device Authorization Grant and automated Private Key JWT authentication, with confirmation/elicitation for destructive operations via the MCP Elicitation API.

h1-brain

h1-brain is an MCP server that connects an AI assistant to HackerOne. It syncs a user’s rewarded reports, programs, and scopes via the HackerOne API into a local SQLite database, queries a pre-bundled database of public disclosed bounty reports, and exposes MCP tools (notably hack(handle)) to search/analyze that data and generate structured attack briefings.

mcp-scan

mcp-scan is a locally-run CLI security scanner for Model Context Protocol (MCP) server configurations. It auto-detects configurations for multiple AI tool clients and performs checks such as secret exposure, prompt injection risk, supply-chain/package risk, data exfiltration indicators, and permission/transport issues. It can output JSON and integrate with GitHub Actions via SARIF.

agentshield

AgentShield is a security auditor/scanner for Claude Code agent setups. It scans local Claude configuration directories (e.g., ~/.claude/ and .claude/), detects hardcoded secrets, permission misconfigurations, unsafe hook behaviors, MCP server risks, and prompt/prompt-injection style vulnerabilities, and can output graded reports plus optional auto-fixes for certain issues.

delinea-mcp

Provides an MCP server that exposes tools for interacting with Delinea Secret Server APIs (and optionally Delinea Platform user management). It supports OAuth 2.0 with dynamic client registration, and can run over stdio (for local/desktop connectors) or SSE/HTTP transport.

Viper

An open-source adversary simulation and red team platform covering the full MITRE ATT&CK lifecycle, with 100+ post-exploitation modules, multi-platform implants, LLM-powered automated decision-making, and a visual team dashboard. Positioned as a free alternative to Cobalt Strike.

node9-proxy

@node9/proxy (Node9) is an execution security layer for agentic AI tools. It intercepts potentially dangerous shell/file/DB actions and MCP tool calls before execution, performs DLP scanning for secrets, routes high-risk actions through a human-in-the-loop approval “race engine” (native popup/browser/terminal/Slack), and can snapshot/undo file edits via shadow Git snapshots. It also supports an MCP Gateway as a transparent stdio proxy between AI clients and MCP servers.

CloudSword

Cloud security assessment tool for Chinese cloud providers (Alibaba, Tencent, Huawei, Baidu, Qiniu). Enumerates cloud assets (storage buckets, compute instances, IAM users/roles, domains), tests access permissions, hardens bucket policies, and creates honey tokens for intrusion detection. Has a Metasploit-like CLI interface and MCP protocol support via SSE and STDIO modes.

ironcurtain

IronCurtain is a TypeScript runtime/CLI for autonomous AI agents that enforces a human-readable “constitution” (policy) compiled into deterministic rules. It mediates all agent tool calls via MCP servers (e.g., filesystem/git/github/workspace) and a policy engine that allows/denies/escalates actions for user approval, with agent code isolated in a V8 sandbox (builtin mode) or an external agent constrained by Docker + network/MCP mediation (docker mode).

MCP Kali Server

A lightweight Flask API bridge that connects Claude Desktop (or any MCP-compatible client) to a Kali Linux machine, enabling AI-assisted command execution for authorized penetration testing and CTF challenges. The server exposes a thin HTTP API on port 5000 that accepts arbitrary shell commands and returns their output, effectively giving an AI assistant a live Kali terminal. Tools like Nmap, Metasploit, sqlmap, Gobuster, enum4linux, and any other Kali tool are accessible by name. The architecture is intentionally minimal — a single Flask server with no auth, no sandboxing, and no command filtering — making it fast to set up for isolated testing environments but completely unsuitable for production or shared infrastructure.

mcp-scanner

mcp-scanner is a Python tool/SDK/CLI that scans MCP servers and their exposed tools/prompts/resources/instructions for potential security issues. It supports multiple analysis engines (static YARA rules, an LLM-as-judge workflow, and Cisco AI Defense “inspect” API), plus offline JSON scanning, stdio/remote MCP connections, and optional VirusTotal-based malware detection via hash lookups.

iam-policy-autopilot

IAM Policy Autopilot is an open-source tool (CLI + MCP server) that performs deterministic static analysis of application code to generate baseline AWS IAM identity-based policies (and optionally help fix AccessDenied errors). It targets building/iterating IAM permissions for application roles using local code inspection.

autopentest-ai

AutoPentest is an agentic pentesting MCP server for web applications. It orchestrates multiple role-specialized agents (Scout/Analyzer/Exploiter/Reporter) across a structured multi-phase workflow that crawls and maps an application, then performs OWASP WSTG-aligned testing and PortSwigger technique-based exploitation attempts, producing evidence-backed reports and doing quality-gated verification. It also bundles security tooling in Docker and includes browser-based testing via a Playwright MCP component (per README).

MCPScan

MCPScan (mcpscan) is a CLI tool that discovers and audits Model Context Protocol (MCP) servers/configs and checks for security issues such as tool poisoning, credential leakage, overprivileged capability combinations, missing authentication, session hijacking indicators, SSRF vectors, RCE vectors, and supply-chain/CVE-related risks. It supports scanning stdio MCP servers (spawned via a command), scanning HTTP/SSE MCP endpoints, and optionally probing localhost for exposed HTTP MCP servers; outputs include terminal, JSON, and SARIF.

MetasploitMCP

MetasploitMCP is an MCP server that bridges MCP clients (e.g., Claude Desktop via STDIO or other MCP clients via HTTP/SSE) to the Metasploit Framework using the Metasploit RPC service (msfrpcd). It exposes MCP tools for discovering exploit/payload modules, running exploit/auxiliary/post modules, managing sessions and listeners, and generating payload files.

agentidentityprotocol

Agent Identity Protocol (AIP) is an open-source, zero-trust security layer intended to secure MCP/tool-calls for autonomous agents by issuing/verifying cryptographic agent identity tokens (AATs), enforcing per-tool/per-argument authorization via a policy engine (optionally with human-in-the-loop approval), performing DLP scanning on requests/responses, and writing JSONL audit logs tied to verified identity.

agent-scan

Command-line security scanner that inventories and scans locally installed agent components (MCP server configurations, MCP tool descriptions, and optionally agent skills) for common agent-supply-chain threats such as prompt injection, tool poisoning/shadowing, toxic flows, malware payloads, untrusted content, and credential/secret handling issues.

apkleaks

APKLeaks is a CLI tool that statically scans Android APK files to find potentially sensitive information such as URIs/endpoints and secrets, using the jadx disassembler (and other tooling) plus configurable regex-based patterns.

DocSentinel

DocSentinel is a Python/FastAPI MCP-ready service that parses security documents (PDF/DOCX/XLSX/PPTX/text), indexes an organization’s security policies into a knowledge base (RAG), and uses configurable LLM backends to generate structured security assessment reports (risks, compliance gaps, and remediation suggestions). It exposes REST endpoints for assessments and knowledge-base operations and includes an MCP server for agent integration.

evil-mcp-server

Provides a Model Context Protocol (MCP) server (stdio or HTTP mode) with tools intended for security red-team testing. The README describes a tool, record_analytics, that simulates exfiltration/analytics behavior for security demonstrations.

medusa

MEDUSA is an open-source (Python) AI-first security scanner/CLI that detects vulnerabilities and insecure patterns in traditional code as well as AI/ML and agent/LLM application artifacts (including prompt-injection style rules, RAG pipeline risks, MCP server configurations, and repo poisoning via editor/agent configuration files). It also supports scanning local directories and (optionally) cloning/scanning GitHub repos via a --git flag, producing reports in multiple formats (JSON/HTML/Markdown/SARIF).

oracle.oci-web-application-acceleration-and-security-mcp-server

MCP server for Oracle OCI Web Application Acceleration and Security (WAAS) service, enabling AI agents to manage combined CDN acceleration and security policies, configure WAF rules, manage access control lists, and monitor web application protection on Oracle Cloud Infrastructure.

oracle.oci-web-application-firewall-mcp-server

MCP server for the Oracle OCI Web Application Firewall (WAF) service, allowing AI agents to manage WAF policies, protection capabilities, request access control, and threat intelligence configurations on Oracle Cloud Infrastructure.

oracle.oci-network-firewall-mcp-server

An MCP server that exposes Oracle Cloud Infrastructure (OCI) Network Firewall service APIs, enabling AI agents to manage next-generation firewall policies, security rules, URL filtering lists, application groups, and firewall instances within OCI virtual networks.

burp-mcp-server

Provides an MCP server (stdio for Claude Desktop, and an HTTP mode for testing) that integrates with BurpSuite via the Montoya API to trigger scans, retrieve scan results, and access proxy/traffic history and scan queue/issue resources.

security-scanner-mcp-server

Evaluates source artifacts for security issues via an MCP (Model Context Protocol) server interface, intended to be used by AI agents to run or orchestrate scanning workflows.

snyk-mcp-server

An MCP server that integrates Snyk functionality into an agent workflow via the Model Context Protocol, enabling agents to perform Snyk-related security/vulnerability queries and actions through MCP tools.

mcp-servers

Monorepo providing multiple TypeScript Model Context Protocol (MCP) server packages for Check Point security platforms (e.g., management, management logs, threat prevention, HTTPS inspection, Harmony SASE, reputation, gateway CLI diagnostics, threat emulation, GAIA, documentation assistant, CPInfo analysis, Argos ERM, and policy insights). Each MCP server is intended to expose a structured interface to query and analyze security-related data.

mighty-security

CLI/tooling to scan and analyze MCP servers for potentially malicious behavior (e.g., command injection, SSRF, credential/env leakage, path traversal). Includes an optional LLM mode (Cerebras) and mentions a web dashboard for monitoring/scans and exporting reports.

AI-Infra-Guard

AI-Infra-Guard (A.I.G) is an AI red-teaming and security assessment platform that runs multiple scanners and evaluations, including OpenClaw security scanning, multi-agent workflow security scanning, MCP server/agent-skills scanning, AI infrastructure/component vulnerability scanning, and LLM jailbreak/prompt security evaluations. It exposes a web UI and a documented set of task-creation APIs (Swagger/docs) for running scans and retrieving results.

qu3-app

qu3-app is a Python CLI/client that establishes quantum-safe secure sessions with an MCP server using post-quantum cryptography (Kyber KEM for key establishment and SPHINCS+ for request authentication), then sends encrypted/signed inference and policy-update requests and verifies encrypted/signed responses with server attestations. It also includes a FastAPI mock MCP server for local development/testing.

TriageMCP

TriageMCP is an MCP server intended to perform basic static triage of Windows PE (Portable Executable) files using tooling such as pefile and YARA, returning analysis results to an LLM-driven workflow.

burp-mcp-agents

Provides guides and helper scripts to connect a Burp Suite MCP Server to different AI backends (Codex CLI, Gemini CLI, Ollama, LM Studio), including a recommended Caddy reverse proxy setup for MCP over SSE and reusable prompt templates for analyzing real (passively observed) Burp traffic.

MCP-Scanner

A Python command-line security research tool that uses the Shodan API to discover potentially exposed Model Context Protocol (MCP) servers, probes them over HTTP and Server-Sent Events (SSE), verifies MCP protocol compliance, enumerates available tools/capabilities, and writes JSON/CSV/log outputs.

mcpsec

mcpsec is a Python CLI toolchain for security scanning and fuzzing of MCP (Model Context Protocol) servers. It can scan MCP servers via stdio or HTTP, enumerate attack surface, run SAST-like checks (Semgrep rules), and perform runtime fuzzing/generation to find crashes and application-layer vulnerabilities (e.g., SSRF/path traversal/RCE-class indicators), with optional AI-assisted payload generation.

mcp-for-security

Provides multiple Model Context Protocol (MCP) server implementations that wrap common security testing tools (e.g., SQLMap, Nmap, FFUF, Nuclei, Masscan, etc.) so they can be invoked via a standardized MCP interface, including a Docker image approach for deployment.

oracle.oci-zero-trust-packet-routing-mcp-server

MCP server for Oracle OCI Zero Trust Packet Routing (ZPR), enabling AI agents to manage security policies that control packet routing at the network layer using zero-trust principles on Oracle Cloud Infrastructure — defining which workloads can communicate with each other based on identity rather than IP addresses.

opgen-mcp-server

An MCP server that exposes tools for generating passwords/phrases (character-based and word-based) and copies the generated password to the clipboard.

security-investigator

security-investigator is a Python-based security investigation automation framework that uses VS Code Copilot/Agent Skills and Microsoft MCP servers to run natural-language driven investigations across Microsoft Sentinel and Defender XDR/Entra (Graph API), enrich indicators with threat-intel sources, generate KQL-based analyses and HTML/SVG reports, and supports multiple specialized “agent skills” (e.g., incident/user/device/IoC investigations, posture audits, drift detection, visualization, custom detection authoring).

myssl-mcp-server-go

myssl-mcp-server is an MCP server (Go) that exposes tools to query MySSL-based domain/IP security information (domain_check) and to check MySSL service health (health_check), intended to be used by compatible AI clients via the MCP protocol using MySSL AccessKey/SecretKey credentials.

certbot

Certbot is an ACME client used to obtain and renew TLS/SSL certificates from certificate authorities (commonly Let’s Encrypt) and configure/validate domains via supported plugins (e.g., webserver or standalone modes).

mcp-armor

mcp-armor is a local Python CLI tool that auto-discovers and scans Model Context Protocol (MCP) configurations (for popular agent/IDE setups), inventories MCP tools/resources/prompts, runs static security checks (e.g., prompt injection, tool poisoning/shadowing, secret detection), and optionally performs baseline drift detection via an inspect/scan workflow that flags deviations from an approved baseline.

kubescape-mcp-server

Kubescape MCP Server is a middleware that exposes Kubescape Kubernetes vulnerability manifests and related querying capabilities via the Mark3 Labs MCP protocol over stdio. It supports listing vulnerability manifests for image/workload levels, listing vulnerabilities in a manifest, and listing vulnerability matches for a specific CVE, also exposing manifest data through MCP resource templates.

ENScan GO

Collects Chinese enterprise information from multiple commercial APIs (AiQiCha, TianYanCha, etc.) for security research. Aggregates ICP registrations, mobile apps, WeChat accounts, subsidiaries, job postings, and software copyrights into unified output. Includes an MCP server mode for AI assistant integration.

onecli

OneCLI is an open-source gateway and dashboard that stores encrypted credentials for AI agents and transparently injects the right secrets into outbound HTTP requests made by those agents, so the agents never directly handle the real API keys. It uses a Rust HTTP gateway for request interception and a web dashboard for managing agents, secrets, and permissions; optionally it can integrate with external vaults (e.g., Bitwarden) for on-demand credential injection.

theHarvester

theHarvester is an OSINT reconnaissance tool that gathers externally visible information about a target domain, including names, emails, IPs, subdomains, and URLs by querying multiple public resources (passive modules) and optionally running active enumeration and screenshots.

MCPHammer

MCPHammer is a Python-based Model Context Protocol (MCP) server (FastMCP over HTTP) that exposes multiple MCP tools, including an Anthropic/Claude query tool, local file execution, URL-based download-and-execute, server info/health endpoints, and configurable “injection” text plus remote management via a separate configuration server. It also supports session logging and a web UI for managing instances and updating configuration (e.g., injection text and init URL).

h8mail

h8mail is a Python CLI tool for email OSINT and “breach hunting” style lookup. It matches email patterns from inputs/files/URLs, searches local breach datasets (e.g., BreachCompilation / Collection1-style dumps), and can query multiple third-party breach/recon services (including HaveIBeenPwned and others) for related emails, cleartext credentials, and/or password/hash intelligence depending on the provider and API keys.

mcp-security-checklist

Provides a community-maintained security checklist (human-readable docs plus machine-readable checklist.json/checklist.yaml) for securing Model Context Protocol (MCP) server deployments and agent infrastructure, covering topics like authentication/authorization, input validation/prompt injection, tool exposure, session security, observability, and network hardening.

ramibot

RamiBot is a self-hosted, local-first AI security operations chat application that integrates multiple LLM providers with an MCP-powered security-tool pipeline. It runs security tooling inside Docker (including a dedicated rami-kali MCP server), supports Tor proxy routing, maintains local SQLite conversation/history, gates tool execution with a human-in-the-loop approval step, and enforces evidence-locked reporting to reduce fabricated findings.

security-mcp-server

An MCP server package intended to expose “security” related capabilities to an AI agent via the Model Context Protocol (MCP).

drozer

drozer is an open-source Android security testing framework that lets a user interact with a connected Android device/emulator by assuming the role of an app. It can enumerate and probe app components and IPC endpoints, execute modules, and install/run a drozer agent on the device (typically via adb).

heimdall

heimdall is a Go-based library/CLI framework for implementing request signing and verification (in the style of an HMAC/secret-based guard) to authenticate clients and protect endpoints. It focuses on generating and validating signed requests/tokens to ensure integrity and authenticity.

ClawVault

ClawVault is a Python-based AI security “vault” that provides a transparent proxy/gateway to intercept and monitor traffic between AI tools and external model APIs, apply guard/sanitization rules (sensitive data detection, prompt-injection defense, dangerous command blocking), track token budgets, and expose a dashboard for configuring agent-level policies and performing tests.

fail2ban

Fail2ban is a host-based intrusion prevention tool that monitors log files (e.g., for SSH failures) and automatically bans IP addresses that match configured patterns/rules, using configurable ban actions and whitelists.

mcp-shield

mcp-shield is a CLI security scanner that inspects installed MCP server configurations/tools and reports potential prompt-injection/tool-poisoning style vulnerabilities, suspected data-exfiltration channels, tool shadowing/behavior modification, and cross-origin escalation risks. It can optionally use an Anthropic Claude API key to enhance analysis.

letsencrypt

letsencrypt (commonly refers to the Let’s Encrypt certificate authority and the tooling/ecosystem used to obtain and renew TLS certificates) enables automated issuance and renewal of X.509 certificates for domains using ACME challenges.

docs-mcp

The Antora playbook project for Redpanda documentation.

Ciphey

Ciphey is a CLI/command-line tool (with a Python importable entrypoint) that attempts to automatically decrypt/decode or otherwise transform unknown ciphertext-like input into readable plaintext. It uses cipher/hash/encoding detection plus language/plaintext checking, and supports many classical ciphers and common encodings/hashes.

frida-c2-mcp

frida-c2-mcp (FridaC2MCP) is an MCP server that exposes Frida dynamic instrumentation over a networked, streamable HTTP transport. It is intended to run entirely on rooted Android and jailbroken iOS devices, translating MCP/HTTP requests into Frida operations such as process/application management, attaching sessions, and executing/injecting bundled JavaScript Frida scripts.

mcp-audit

mcp-audit is a Python CLI (and web app) that scans for Model Context Protocol (MCP) configurations across developer tools and GitHub repos, detecting potential exposures such as secrets (API keys/tokens/DB URLs), connected APIs/endpoints, configured AI models, and risk flags (e.g., shell/filesystem access). It can export reports in multiple formats (JSON, SARIF, CycloneDX, etc.) and can be used in CI to fail builds on critical findings.

MCP-Defender

MCP Defender is a desktop application that proxies MCP tool-call requests and responses from supported AI apps (e.g., Cursor, Claude, VS Code, Windsurf) through the Defender. It inspects the intercepted traffic against signature rules and prompts the user to allow or block tool calls when harmful patterns are detected.

stealerlogs-mcp-server

MCP server package intended to expose log-stealing-related functionality to an AI agent via the Model Context Protocol (MCP).

routersploit

RouterSploit is an open-source Python exploitation framework for embedded devices. It provides modular components for exploitation, credential checking, vulnerability scanning, payload generation, and generic attacks, run via a CLI entry point (e.g., rsf.py) and optionally via Docker.

spamassassin

SpamAssassin is an open-source email spam and malware-adjacent filtering system. It scores incoming email using configurable rules (e.g., Bayesian learning, DNS-based checks, and pattern/rule matching) and can produce a classification result (spam/ham) and add headers for downstream processing.

mcp-server-scoutsuite

An MCP server package (mcp-server-scoutsuite) intended to expose ScoutSuite functionality to AI agents via the Model Context Protocol. From the provided input, no README/repo content or manifest details were included, so the exact tools/capabilities, endpoints, and behavior cannot be verified.

fsociety

Fsociety is a Python-based penetration testing “tools pack” bundling many third-party security utilities across reconnaissance, password attacks, wireless testing, exploitation, sniffing/spoofing, web hacking, and post-exploitation. The README describes it primarily as a collection/framework to install and run these tools.

onionize

Onionize is a tool/package (based on its name and typical usage in this ecosystem) intended to route or transform web traffic through an anonymity layer (e.g., Tor) so requests can be made with increased privacy/anonymity.

tls-mcp-server

The package name suggests an MCP (Model Context Protocol) server focused on TLS-related capabilities (e.g., inspecting or managing TLS/HTTPS configuration). However, no README, repository metadata, code, or manifest was provided in the prompt, so concrete features, endpoints/tools, and configuration details cannot be verified.

beagle-security-mcp-server

Beagle-security-mcp-server appears to be an MCP (Model Context Protocol) server package intended to expose security-related capabilities to LLM agents via MCP tools. However, no README/repo manifest content was provided in the prompt, so the concrete tool surface area, auth model, and behavioral details cannot be verified.

tacacs_server

TACACS+ server component for AAA (authentication, authorization, and accounting). Typically provides a network service that accepts TACACS+ requests from network devices and applies configured authentication/authorization/accounting policies.

signserver-ce

signserver-ce is an open-source certificate signing service (“signserver”) that signs CSRs on behalf of an organization (e.g., issuing end-entity certificates) and typically exposes an administrative and/or client-facing API for submitting signing requests and retrieving results, along with supporting configuration for key material, signing policies, and authentication/authorization.

wifite2

Wifite2 is a CLI Python tool that automates wireless network auditing by orchestrating external wireless attack utilities (e.g., Aircrack-ng suite tools, reaver/bully for WPS, and hashcat-related tools for PMKID). It scans for targets, captures handshakes/PMKID/WEP-related artifacts, and attempts to crack passwords using the enabled attack methods.

Bombers

“Bombers” is an archived Python collection linking to multiple scripts/tools for SMS/Email/WhatsApp/Twitter/Instagram spamming/bombing and “fake/temporary SMS” utilities intended to bypass phone-based verification. It primarily functions as an index of other repositories and some referenced local scripts (e.g., SMS_bomber.py, Email_bomber.py, Twitter_bomber.py).

awesome-mcp-security

awesome-mcp-security is a curated registry/listing of MCP servers along with a daily-updated “Trust Score” intended to help AI agents assess the safety of using particular MCP servers (i.e., attack-surface/prompt-injection/tool-poisoning risk), not the underlying code quality of those servers.

Clarid Compliance

Check bank marketing for FDIC, NCUA, TILA, Reg DD, Reg Z, UDAAP, and Equal Housing compliance.

dkvdm/onepassword-mcp-server

MCP server for interacting with 1Password via the CLI

Gmail

Google Sheets

IncomeBot Trading Intelligence

MCP-Bastion

Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.

mcp-docs

MCP Fortress

mcp-watchdog

Outlook

security-controls

server

WaveGuard

Anomaly detection API powered by physics simulation. Scan any data for outliers.

Ybe Check

Ybe Check – security and compliance orchestrator for AI-generated repositories.

yuhuison-mediawiki-mcp-server-auth

衍象坊 · 奇门遁甲 & 大六壬

Qimen Dunjia & Da Liu Ren divination: complete nine-palace charts and four-lesson analysis.

openssh-server

OpenSSH Server (sshd) provides secure remote access to machines using the SSH protocol (e.g., interactive shell, command execution, and SFTP). It handles authentication, encryption, key exchange, and session management for inbound SSH connections.

pentest-mcp-server

Provides an MCP (Model Context Protocol) server intended to enable autonomous penetration testing workflows via a locally accessible server/UI (example localhost:8080) on Linux distributions such as Kali Linux and Parrot OS.

awesome-hacking

awesome-hacking is a curated list (an “awesome” repository) of hacking/security-related tools and resources. It is not, by itself, an API/service; it primarily provides links and pointers to third-party tools.

burp-server

burp-server appears to be a local service/interface for running Burp Suite-related server automation/integration, likely exposing functionality over a network interface so other tools (including agents) can interact with Burp.

ungoogled-chromium

unGoogle-chromium is a hardened Chromium build/distribution project that removes or changes Google-specific services and defaults, aiming to improve privacy by reducing telemetry and web-service integrations while maintaining Chromium compatibility.

ldap-server

ldap-server is an LDAP server implementation/package intended to run an LDAP service for directory/authentication use cases (e.g., providing LDAP endpoints that clients can bind to and query).

xroad-security-server-sidecar

xroad-security-server-sidecar appears to be an add-on component (“sidecar”) for the X-Road ecosystem focused on server-side security capabilities. Based on the name alone and without repository/README content, its exact functions, network interfaces, and configuration model cannot be verified.

psono-server-enterprise

pSno (psono-server) enterprise server component for hosting and managing password/data vault functionality (self-hosted service).

vault-server

vault-server appears to be a server component for HashiCorp Vault–style secret management, but the provided prompt includes no README/repo metadata or manifest content to confirm scope, interfaces, or operational details.

ossec-server

ossec-server appears to be a server component related to OSSEC/Wazuh-style security monitoring (agent/server architecture for log/syscheck-based security alerts). Without the README/repo metadata, the evaluation focuses on interface/auth/pricing/documentation that are not provided here.

krb5-server

krb5-server appears to provide a Kerberos 5 (krb5) server component/service for issuing and validating Kerberos tickets (authn) in a networked environment. It is intended for deploying Kerberos KDC/auth services rather than as a client library.

cyclonedx-bom-repo-server

CycloneDX BOM repository server for storing, indexing, and serving CycloneDX Software Bill of Materials (SBOMs) (BOMs) in a repository-like service.

keeper.sh

keeper.sh appears to be a service for securely storing/handling secrets ("keeper"), but the provided prompt contains no README/repo/package manifest content describing its exact API, capabilities, or usage.

kms-server

No repository/README/package manifest content was provided for kms-server, so its capabilities, APIs, auth, pricing, and operational behaviors cannot be determined from observable facts.

kms-server

Insufficient information was provided about the kms-server package (no README/repo metadata/code/package manifest). As a result, the service’s actual functionality, interfaces, auth model, and operational characteristics cannot be verified.

kms-server

kms-server appears to be a server implementing key-management/crypto operations (KMS-like). However, no README/repo/package manifest content was provided in the prompt, so concrete features, API surface, auth, and operational characteristics cannot be verified from evidence.

kms-server

Insufficient information provided to evaluate kms-server (no README/repo/package manifest content was included).

notary-server-photon

notary-server-photon appears to be a “notary” server component, likely providing a network service for notarization/attestation workflows (e.g., signing, timestamping, or verification). However, no README/repo or manifest content was provided in the prompt, so the exact capabilities, endpoints, and operational details cannot be verified from observable facts.

passky-server

passky-server appears to be a server component related to “passky” (likely a password/passkey-related service), but no README/repo/manifest content was provided in the prompt to verify its actual functionality, endpoints, auth model, or operational behavior.

scrutiny

Scrutiny appears to be a package for code/repo auditing or static checks, likely producing findings from source inputs; however, no repository README/manifest content was provided in the prompt, so the exact functionality cannot be verified.

tor

tor (commonly Tor Browser / Tor project software) is used to route network traffic through the Tor anonymity network to reduce tracking and provide privacy against network-level observers.

xroad-security-server

Insufficient information provided to evaluate this package. Only the package name (xroad-security-server) was given; no README/repo contents, API/interface description, auth model, pricing, or operational documentation was included.

ad-password-changer

adversary-mcp-server

MCP server for security vulnerability scanning and detection

agentaudit

Security scanner for AI agent packages — CLI + MCP server

agent-identity-mcp-server

MCP Server for AI agent identity and authorization — create, verify, and manage agent identities

airtable-mcp-server-oauth-fastmcp

Airtable OAuth MCP Server - Python implementation with OAuth 2.0 authentication

apcore-toolkit

Shared scanner, schema extraction, and output toolkit for apcore framework adapters

approle-secret-server

app-store-connect

App Store Connect API as MCP: apps, TestFlight, subscriptions, localizations, reports. JWT auth.

arcade-mcp-ts

TypeScript framework for building MCP servers with built-in OAuth (21 providers), secret injection, middleware, multi-user JWT auth, and worker routes. Wraps @modelcontextprotocol/sdk.

armyknife-llm-redteam

LLM red-teaming security scanner — nmap for LLMs

authentication-server

authn-server

authorization-server

auth-proxy-server

authserver

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server

auth-server-rec

auths-mcp-server

Reference MCP tool server with Auths-backed JWT authorization

authy-cli

CLI secrets store & dispatch for AI agents — encrypted vault, scoped policies, run-only tokens, and audit logging

base-security-scanner-mcp

MCP server to scan smart contracts on Base for honeypots, rug pulls, and vulnerabilities.

@bdmarvin/mcp-server-gbp

MCP server for Google Business Profile Performance API.

BoostSecurity

Bright Security

AI-powered application security testing — scan APIs, discover endpoints, and find vulnerabilities.

@cardexscan/mcp-server

MCP server for Cardexscan - Cardano DEX scanner and aggregator

@classroomio/mcp

Thin stdio MCP server for ClassroomIO course authoring.

cle-auth-server

@clerk/clerk-mcp

An MCP server for Clerk generated by @buildwithalyer

component-server-vault-proxy

Context Processor

contract-scanner

Smart contract security scanner — vulnerabilities, risk scores, and calldata decoding

contract-security-scanner

MCP smart contract scanner with NEAR-focused security context.

Contract Security Scanner

Scans Base L2 smart contracts for security risks. Risk score 0-100, detects backdoors & proxies.

Contrast Security

crates-docs

高性能 Rust crate 文档查询 MCP 服务器，支持 Stdio/HTTP/SSE 传输和 OAuth 认证

@cyanheads/toolkit-mcp-server

MCP server providing system, network, geolocation, generator, datetime, and security tools

datagrout-conduit

Production-ready MCP client with mTLS, OAuth 2.1, and semantic discovery

defense-mcp-server

Defense MCP Server — 31 defensive security tools across 29 modules for system hardening and threat detection

devkits

12 local developer tools: JSON, Base64, JWT, regex, hash, UUID, Markdown, diff, cron.

dida365-mcp-server

MCP Server for Dida365 (TickTick) Task Management Integration

donetick-mcp-server

MCP server for Donetick chores management with JWT authentication, Full API support, and 20 MCP tools

e2e_test_secret_server

esk

Encrypted Secrets Keeper with multi-target deploy

etherscan-mcp-server

etherscan v2 api mcp server

excalidraw-mcp-server

Security-hardened MCP server for Excalidraw with API key auth, rate limiting, and real-time canvas sync

exovault-mcp-server

MCP server for ExoVault — read, search, and manage encrypted notes from Claude Code

external-auth-server

fabryk-auth-mcp

MCP auth metadata endpoints for fabryk-auth — RFC 9728/8414 discovery

fastmcp-ironbook

Iron Book agent-based security integration for FastMCP servers

firewalla-mcp-server

@forestadmin/mcp-server

Model Context Protocol server for Forest Admin with OAuth authentication

Fray — WAF Security Testing MCP Server

WAF security testing: 5,500+ payloads, 25 WAF fingerprints, 21 recon checks, bypass AI

gemara-mcp-server

A MCP server for automating the authoring of GRC Risk Assessment documentation in gemara.

Gmail

Gmail integration with OAuth authentication, message search, batch operations, and Sheets export

go-mcp-server-demo

A demo MCP server with go, with oauth and dynamic client registration

go-mcp-server-example

OAuth-Protected MCP Server Example (Go)

Google Sheets

Google Sheets integration with OAuth, spreadsheet management, batch operations, and formatting

@greynoise/greynoise-mcp-server

MCP Server for the GreyNoise Enterprise API

hce-auth-server

iflow-mcp_aws-samples-security_scanner_mcp_server

A Model Context Protocol (MCP) server for security scanning with Checkov, Semgrep, and Bandit

@iflow-mcp/brentmid-evernote-mcp-server

A secure MCP server for Evernote integration with OAuth 1.0a authentication and automatic token expiration handling

iflow-mcp_crazymarky-mcp_nuclei_server

A Nuclei security scanning server based on MCP

iflow-mcp_hypijump31_bluetooth-mcp-server

Bluetooth MCP Server for scanning and interacting with Bluetooth devices

iflow-mcp_jguimera-securitycopilotmcpserver

A Python-based MCP server using FastMCP library that provides integration with Microsoft Security Copilot and Microsoft Sentinel using Azure Identity Authentication

@iflow-mcp/josectoscano-stellar-mcp-server

Stellar's MCP Server

iflow-mcp_MCP-Kali-Server

MCP server for Kali Linux security tools integration

IncomeBot Trading Intelligence

Options trading — regime detection, momentum scanning, income screening, and risk simulation.

ingeniux-cms-mcp-server

Production-ready Ingeniux CMS MCP server with OAuth, Roo integration, and modular architecture.

integrate-sdk

Type-safe 3rd party integration SDK for the Integrate MCP server

irulescan MCP

isc-transforms-mcp

MCP server for SailPoint Identity Security Cloud (ISC) Transform authoring — scaffold, strict lint, catalog, and safe upsert to live tenants.

@jeff-stapleton/auth0-mcp-server

MCP server for managing Auth0 applications via the Management API

Jentic Remote MCP Server

Remote MCP for 1,500+ APIs. Vault-managed credentials; OAuth or API key. Search, load, and execute.

jwt-auth-server

jwt-hack

Hack the JWT (JSON Web Token) - A tool for JWT security testing and token manipulation

jwt-server

jwt-server

jwt-server

kardia-auth-server

@lamy-work/mcp-server

MCP server for Lamy-work API integration with OAuth authentication

legit-oauth-server

letsencrypt

litmuschaos-authserver

mcp

Symbiotic CLI MCP Server for security scanning and analysis

mcp

Sapiom MCP server — authentication, verification, and API tools

@mcp-abap-adt/core

SAP ABAP ADT MCP server with full CRUD for on-prem and ABAP Cloud (BTP), plus JWT/XSUAA and service-key destination auth

mcp-action-firewall

A transparent MCP proxy that intercepts dangerous tool calls and requires OTP-based user approval.

mcp-api

Preview release of FusionAuth API MCP server

mcp-apollo-config

MCP server for Apollo Config Center with portal session authentication

mcp-auth0-audit-ips

An MCP server to analyze auth0 suspicious ips

mcp-auth-middleware

JWE authentication middleware for MCP/Starlette applications

mcp-auth-servers

🔒 Reference MCP servers that demo how authentication works with the current Model Context Protocol spec.

mcp-demo-server

MCP demo server in golang, with OAauth 2.1 support.

mcp-docs

FusionAuth Documentation MCP server

mcp-document-processor

A simple document processor MCP server

mcp-echo-streamablehttp-server-stateful

A stateful diagnostic MCP echo server with 11 comprehensive tools for debugging OAuth flows, session management, and analyzing software engineering excellence

mcp-echo-streamablehttp-server-stateless

An advanced stateless diagnostic MCP echo server with 9 comprehensive tools for debugging OAuth flows and analyzing software engineering excellence

MCP Fortress

Security scanner for MCP servers. Detect vulnerabilities, prompt injection, and tool poisoning.

MCP Gateway

Multi-tenant MCP platform with OAuth 2.1, Entra SSO, RBAC and audit logging.

mcp-gdocs

MCP server for Google Docs, Drive & Comments (OAuth + Service Account)

mcp-googletasks-vrob

Robust Google Tasks MCP Server with persistent OAuth2 tokens

mcp-guard

A lightweight, high-performance security gateway for MCP servers

mcp-guardian

A lightweight guardian/middleware for MCP servers (auth, rate-limiting, logging, WAF, etc.)

mcp-kyvos-server

mcp-kyvos-server is a server implementation that integrates the Kyvos platform with the Model Context Protocol (MCP). It enables users to query Kyvos semantic models using natural language, translating prompts into executable queries and returning results from Kyvos. The server supports both SSE and STDIO communication modes and allows secure authentication using user-provided Kyvos credentials (basic and OAuth2.0).

mcplint

MCP Server Testing, Fuzzing, and Security Scanning Platform

mcp-nmap

MCP Server for Nmap scanning

mcp-nmap-server

MCP server for performing network scanning using NMAP

mcp-oauth2

Minimal, secure OAuth2 authorization library for MCP servers

mcp-oauth-dynamicclient

MCP OAuth Dynamic Client Registration Server - OAuth 2.1 and RFC 7591 compliant

mcp-patch

Security scanner for Python MCP server code

mcp-proxy-adapter

Powerful JSON-RPC microservices framework with built-in security, authentication, proxy registration, queue-backed command execution for long-running operations, and configurable HTTP timeouts for mTLS connections

mcp-proxy-oauth-dcr

MCP Proxy with OAuth Dynamic Client Registration support

mcp-proxy-sigv4

MCP proxy server with AWS SigV4 authentication and OAuth support

mcp-remote-auth-ldraney

Shared OAuth infrastructure for MCP remote servers

mcp-scanner

Security scanner and proxy for MCP (Model Context Protocol) servers

mcpsec

MCP Security Benchmark Framework — vendor-neutral security evaluation for MCP gateways

mcp-security-framework

Universal security framework for microservices with SSL/TLS, authentication, authorization, and rate limiting. Added extensible security adapter system for custom operation validation, structured audit logging, and operation context support. Comprehensive test coverage with 1104+ tests. Fully backward compatible. Requires cryptography>=42.0.0 for certificate operations.

mcp-security-scanner

Security scanner for Model Context Protocol (MCP) servers

mcp-server-bicscan

mcp-server-devutils

Zero-auth MCP server with everyday developer utilities: base64, UUID, hash, JWT decode, cron, timestamps, JSON, regex

mcp-server-everything-wrong

Show case common MCP server security concerns

mcp-server-go

Golang implementation of the streaming MCP HTTP transport with sessions, auth and horizontal scaling

mcp-server-masscan

mcp-server-scanner

detect exposed mcp servers over the internet and enumerate their tools

mcp-server-sslscan

mcp-shield

Trust verification for MCP servers. Check scores, scan for security issues, search 4,200+ servers.

mcp-shield-cli

Security scanner, runtime proxy, and audit logger for MCP servers

mcp-streamablehttp-client

Streamable HTTP to stdio proxy client for MCP servers with OAuth support

mcp-vault

Secure your MCP server configs. Scan, fix, and protect API keys in Model Context Protocol configuration files.

mcp-watchdog

MCP security proxy - detects and blocks 40+ MCP attack classes. Zero config.

microsoft-mcp-server

Microsoft Graph MCP Server - Access Microsoft Graph API through the Model Context Protocol

@missionsquad/mcp-helper-tools

MCP server providing encoding, geolocation, generator, datetime, and security tools

mitre-mcp-server

MCP server providing access to MITRE ATT&CK threat intelligence framework

MochiPDF

Remote MCP server for HTML-to-PDF and screenshots with OAuth and API-key auth.

mock-authz-server

mock-jwt-server

mock-oauth2-server

modsecurity-crs-nginx

ms-qa-oauth-server

mycop

AI Code Security Scanner — detect vulnerabilities in AI-generated code

netsuite-mcp-server

NetSuite MCP Server with OAuth 1.0, Multi-User, Multi-Environment Support

@nohacklabs/mcp-server

MCP server for NoHack security scanning API - query vulnerabilities, secrets, scans, and repo configs

nslookup

DNS lookups, SSL certificates, security scanning, and propagation checks via nslookup.io

@nutrient-sdk/dws-mcp-server

MCP server for Nutrient DWS Processor API

nvd-cve-mcp-server

MCP server for searching and retrieving CVE vulnerability information from NVD

oak-scss

SCSS CSS preprocessor language parser with support for modern CSS features and dynamic styling.

oauth2-test-server

A fast, fully configurable, in-memory OAuth 2.0 + OpenID Connect authorization server for testing, zero-HTTP mode and DCR support for testing auth flow in MCP Servers and MCP Clients

oauth-server

@offgridsec/kira-lite-mcp

Kira-Lite MCP Server — Real-time security scanning for AI coding assistants

onelogin-oauth2-server

ordinals-mcp

MCP server for Bitcoin Ordinals, BRC-20, and Runes -- 23 tools via Hiro, Ordiscan, and Magic Eden APIs

Outlook

Outlook integration with OAuth, message search, batch operations, and calendar management

OWASP ZAP MCP Server

MCP server for OWASP ZAP vulnerability scanning with Docker management

oxidized-agentic-audit

Security scanning for AI agent skills — scans skill directories for dangerous bash patterns, prompt injection, supply chain risks, secret leakage, and frontmatter quality issues

pAIchart MCP Hub

MCP Hub: AI service discovery, per-user OAuth, and multi-service workflow orchestration

PaperLink

Document sharing, invoicing, and personal finance platform. 15+ AI tools via OAuth 2.1.

Paradex Trading

MCP server for Paradex perp trading. Market data, accounts, orders, positions, and vaults.

pedant-mcp

MCP server exposing pedant security and capability analysis

pep

Policy Enforcement Point - OIDC authentication and authorization library

perfai-mcp-server

PerfAI MCP Server - Security, Design & Quality Analysis with Auth0 Authentication

phonetik

Phonetic analysis engine for English. Rhyme detection, stress scanning, meter analysis, and syllable counting with a 126K-word embedded dictionary.

@prmichaelsen/acp-mcp

MCP server for a remote machine MCP server that will be wrapped by /home/prmichaelsen/mcp-auth

@procedure-tech/mcp-google

MCP server for multi-Google-account access (Gmail, Calendar, Drive)

@processon/mcp-server-processon-node

ProcessOn MCP Server - create mind maps from markdown

processor-hello-py

@prontiq/ariscan-mcp

MCP server exposing read-only ARI readiness data

pvault-server

RAD Security

registration-processor-dmz-packet-server

registration-processor-dmz-packet-server

registration-processor-dmz-packet-server

registration-processor-dmz-packet-server

registration-processor-dmz-packet-server

remote-mcp-kernel

A microkernel-based MCP (Model Context Protocol) server with OAuth authentication and multiple transport protocols

rubydex-mcp

Security research package — dependency confusion proof of concept. This is a harmless placeholder registered as part of authorized bug bounty research. Contact: security researcher via HackerOne.

ruiss-auth-server

scan-mcp

Scanova MCP Server

secrets_server

securecode

Secrets vault for Claude Code with audit logs, access rules, and AES-256 encryption.

securegit

Zero-trust git replacement with 12 built-in security scanners, LLM redteam bridge, universal undo, durable backups, and a 50-tool MCP server

security-controls

1,451 security controls across 261 frameworks with bidirectional mapping

security-review-mcp

Security Review MCP server (pure Node/TypeScript, npx-ready)

Sensact

An authenticated remote MCP server for user-owned devices and one-shot capability invocation.

server

Create and manage your own Certificate Authority for internal HTTPS.

shredos_scan

SkillsSafe Security Scanner

AI skill security scanner. Detects prompt injection, credential theft, ClawHavoc. Free, no signup.

@socketsecurity/mcp

Socket MCP server for scanning dependencies

solesonic-mcp-server

An enterprise-grade MCP server with built-in federated identity support for SSO across providers and secure, scalable access management.

spring-6-auth-server

sso-server-proxy

sts-secret-server

@supersafe/mcp

SuperSafe MCP server — scan URLs for security vulnerabilities from Claude Code

@takescake/1password-mcp

MCP server for 1Password service accounts — tools, prompts, and resources for vault and credential management

tdr-auth-server

to-auth-server

tomoscan-server

vault

Secret and credential management MCP — securely store, retrieve, manage API keys and tokens

vault-mcp-server

vault-radar-mcp-server

vault-server

vault-server

@vaulttools/mcp-linux-x64

VaultTools MCP server binary for Linux x64

vaultwarden-server

vibescan-mcp-server

MCP server for VibeScan — scan projects for leaked secrets and security issues

@vncy/persona-mcp

Global Persona & Relationship Vault MCP server

@waftester/cli

WAFtester — the most comprehensive WAF testing CLI & MCP server

web-recon-agent

Owned-target web security assessment MCP server for authenticated, high-friction apps.

wireshark-mcp

Professional network analysis with tshark. Security audits, deep-dives, and threat detection.

wkp-mock-authz-server

x-com-mcp-server

MCP server implementation for X.com API with OAuth 2.0 support

yuhuison-mediawiki-mcp-server-auth

Connect to your MediaWiki using simple credentials and manage content without OAuth. Search, read,…

zauth

zitadel-mcp-server

MCP server for Zitadel identity management — manage users, projects, apps, roles, and service accounts

zvault-cli

ZVault CLI — AI-native secrets manager. Import .env files, inject secrets at runtime, MCP server for AI coding assistants