Packages

Provides a local, read-only MCP server that wraps the CData JDBC Driver for Azure DevOps, exposing Azure DevOps entities as SQL-accessible “tables” and making them available to MCP clients (e.g., Claude Desktop) via tool calls like get_tables, get_columns, and run_query over stdio.

Provides an MCP-enabled interface to Cutter (reverse engineering tool). It exposes Cutter operations (listing functions/globals/strings/segments, decompiling/disassembling, xrefs, renaming, comments/types, and reading bytes/addresses) via a local HTTP plugin inside Cutter and an MCP wrapper that can run in STDIO or streamable HTTP mode.

Provides an MCP server (Model Context Protocol) with tools to search YouTube videos, fetch video information by ID, and retrieve English or Russian subtitles. Can run over SSE (default) or stdio on the specified host/port.

Provides a local, read-only Model Context Protocol (MCP) server for exposing IBM Informix (via CData JDBC Driver for IBM Informix) as MCP tools so an AI client (e.g., Claude Desktop) can query live data without writing SQL.

LYRAIOS (llm-os) is a Python-based AI “operating system” that provides a Streamlit UI and FastAPI backend, integrating with the Model Context Protocol (MCP) to connect AI agents to external tools/services. It also includes built-in assistants/tools such as web search, financial analysis, file management, research via Exa, and (partially) Python code execution. It supports authentication via API keys and offers rate limiting/quotas as part of a security & access control layer.

An MCP (Model Context Protocol) gateway/registry that centralizes MCP server discovery and management, virtualizes HTTP services as MCP tools, and exposes MCP-compatible transports (e.g., HTTP JSON-RPC, SSE, WebSocket, streamable HTTP, stdio bridge) behind an enterprise-style API gateway with authentication, RBAC, rate limiting, logging/auditing, and content filtering.

mcp-ssh is an MCP (Model Context Protocol) server that bridges AI clients to SSH functionality. It lets an AI assistant create/manage SSH connections, execute commands (including composite commands), manage tmux sessions, and perform file and process operations on remote servers using structured MCP tool calls.

mem-agent-mcp is a Python MCP (Model Context Protocol) server that connects an “obsidian-like” local Markdown memory store (user.md + entities/*.md) to LLM clients (e.g., Claude Desktop, Lm Studio, Claude Code) for memory retrieval and memory-related tool operations. It also documents memory import/connector workflows (chatgpt, notion, nuclino, github, google-docs) and ways to run the model backend locally (MLX on macOS or vLLM/OpenAI-compatible via LiteLLM proxy).

This repository provides practical resources and example implementations for the Model Context Protocol (MCP): guides for building MCP clients/servers, an MCP TypeScript template repo (linked), a utility (mcp-reporter), and links to multiple example MCP server projects (e.g., filesystem, git, GitHub, Obsidian, PubMed, Perplexity, etc.).

Provides a local MCP Server (stdio-based) that exposes Odoo data via CData’s JDBC Driver. It supplies MCP tools to list tables/columns and run read queries (and documentation mentions CRUD generally, but tools listed are get_tables/get_columns/run_query).

An MCP server that lets MCP clients (e.g., Claude Code) interact with Prefect resources for monitoring/inspection and some automation-like CLI-backed mutations (e.g., triggering deployments, cancelling runs). It authenticates to Prefect using local Prefect configuration or environment variables/HTTP headers, and can be run locally via stdio or deployed over HTTP (e.g., FastMCP Cloud).

An MCP (Model Context Protocol) server that lets AI clients query Prometheus: it summarizes service health, lists metrics/metadata, runs PromQL queries (instant and range), and provides some administration-style views (targets, alerts, settings) by connecting to a configured Prometheus URL.

Provides a Zed context server extension that integrates the Webflow MCP Server, configured via a Webflow token, so Zed’s Agent Panel can use Webflow-related actions/data through MCP.

Provides a local, read-only MCP server that exposes ADP data through a simple MCP tool interface backed by CData JDBC Drivers. Intended for use with AI clients (e.g., Claude Desktop) to query live ADP information via natural-language requests or JSON-RPC tool calls.

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.

Firmware that turns an ESP32 microcontroller into a WiFi NAT router with firewall ACLs, WireGuard VPN, DHCP, port forwarding, packet capture, and WPA2-Enterprise support. Includes a beta MCP server bridge that allows AI assistants to control the router's network operations.

A Playwright-based MCP server that performs Google searches by automating a local browser. Extracts search results, captures screenshots, and retrieves raw HTML without requiring any API keys. Includes anti-bot fingerprinting and browser state persistence.

Provides an MCP server (Model Context Protocol) exposing read-only querying tools for Istio resources and related Envoy proxy configuration/status from Kubernetes clusters.

LeanMCP is a modular TypeScript toolkit for building and deploying MCP (Model Context Protocol) servers, providing an HTTP server runtime plus decorators-based tool/prompt/resource definitions. The README indicates optional modules for authentication, multi-tenancy, request logging, observability, and env/secret injection, along with a CLI for scaffolding and managing MCP projects.

Provides a Model Context Protocol (MCP) server that connects AI assistants to AWS CloudWatch Logs, enabling log browsing/searching, log insights-style querying, summarization, error pattern detection, and cross-service log correlation.