CLI tool and scaffolding generator that creates/extents production-ready Model Context Protocol (MCP) server projects (TypeScript) with prebuilt tools/resources/prompts and test workflows, plus commands to add additional components (tools, resources, prompts, services, transports, utils) to existing projects.

MCP

60

domscribe

Domscribe instruments supported frontend apps to map rendered DOM elements to stable source locations (AST-injected data-ds IDs and a manifest) and to enable agents to query live runtime context from the browser (props/state/DOM snapshots). It also provides a UI overlay for pointing at elements and sending UI-change annotations that agents can claim/implement via MCP.

MCP

60

59

Markplane is a local, markdown-first project management tool for organizing epics, tasks, plans, and notes inside a repository (e.g., .markplane/). It generates a token-efficient .context/ directory for AI assistants and includes a built-in MCP server (JSON-RPC over stdio) plus a local web UI to manage and visualize project state.

MCP

58

A skill/plugin that turns an AI coding/planning agent workflow into a persistent, file-based system (Manus-style). It creates and maintains markdown planning/progress files (e.g., task_plan.md, findings.md, progress.md) and uses IDE/agent hooks to re-read the plan before actions, remind progress updates after tool use, log errors, and verify completion before stopping.

58

ARBuilder

ARBuilder is an AI development assistant for the Arbitrum ecosystem that turns natural-language prompts into Stylus smart-contract code (Rust), cross-chain SDK/bridging and messaging code, and full-stack dApp scaffolding (backend/indexer/oracle/frontend/wallet integration), with additional Orbit chain deployment assistance. It uses a Retrieval-Augmented Generation (RAG) pipeline (hybrid search with vector + BM25 + reranking) and exposes functionality via an MCP server (19 tools), usable either hosted (via an MCP-remote URL and Bearer token) or self-hosted by running the MCP server locally.

MCP

58

mcp-memory-bank

Provides an MCP server that helps AI assistants create and maintain a structured “Memory Bank” (Markdown) for context preservation, including templates, structure descriptions, and suggestions based on a project summary.

MCP

58

mcp-server-make

An MCP (Model Context Protocol) server that exposes a single tool to run GNU Make targets from a specified Makefile (and optional working directory), capturing output and enabling LLM-assisted understanding/execution of build tasks.

MCP

58

gitnexus-stable-ops is a Python/Bash-based production ops toolkit that wraps the GitNexus CLI to keep code intelligence graphs reliable across multiple repositories. It provides diagnostic (doctor/smoke-test), safety-focused impact analysis with fallbacks, and automation scripts for smart and batch reindexing (including embedding preservation, dirty-worktree skipping, and version pinning). It also includes an agent-context graph index/query workflow to support agent swarms.

57

In-Memoria

In Memoria is an on-machine (local-first) MCP server that learns from a codebase and exposes persistent “project blueprint” context, semantic/pattern search, file routing, and work-memory/pattern recommendations to AI coding assistants.

MCP

57

tkinter-mcp-server

A local Model Context Protocol (MCP) server that launches and inspects/controls Tkinter GUI applications. It injects an inspection/controller agent into target Tkinter apps via monkey-patching of tkinter internals, then exposes MCP tools for launching apps, reading the widget tree, capturing screenshots, and interacting with widgets (clicking, focusing, typing, and setting values).

MCP

57

AgentRPC

AgentRPC is a universal RPC layer that allows AI agents to connect to functions deployed anywhere (private VPCs, Kubernetes, multi-cloud) across network boundaries and language barriers. It wraps functions in an RPC interface exposed via MCP and OpenAI-compatible tool definitions.

MCP

57

Provides a Model Context Protocol (MCP) server (Java) that reads Excel-like files (XLSX/XLS/CSV), extracts sheet names, parses header rows into column specs, and reads data rows with values associated to headers. Includes in-memory caching utilities and enforces access to files via an allowed-workspace mechanism configured with env var MCP_WORKSPACES.

MCP

54

yq is a command-line utility for querying and transforming YAML (and related data) using a jq-like syntax. It can read from files or stdin and output transformed YAML/JSON.

53

ava

Ava is an open-source system that helps teams externalize and share development progress by automatically reporting tasks and status updates to Slack. It provides an MCP-compatible HTTP server (served at /mcp) exposing tools for starting/updating/completing tasks and managing blocked/paused state, with OAuth 2.1 (PKCE) protection for MCP clients. It also includes Slack authentication (OIDC), a web dashboard, and Stripe subscription management (checkout/portal and webhook synchronization).

MCP

53

cli

TanStack CLI (@tanstack/cli) scaffolds and manages TanStack Router and TanStack Start applications, and supports adding add-ons. It also provides CLI introspection via JSON output for agent-friendly discovery.

53

quantum-loop

Quantum-Loop is a Claude Code plugin plus scripts that implements a spec-driven autonomous coding loop: it turns a one-line feature description into structured PRD/spec artifacts, builds an execution dependency DAG, runs TDD/quality checks with two-stage review gates, enforces “fresh verification evidence” (Iron Law), and iterates with retry/failure logging until stories pass and then performs cross-story integration before committing changes.

53

ILSpy MCP Server is a Model Context Protocol (MCP) server that lets an AI assistant decompile and analyze .NET assemblies using ILSpy. It supports operations such as decompiling assemblies/types/members, listing and searching types, and analyzing type relationships/hierarchies, intended to be used by MCP-compatible clients.

MCP

52

json-server provides a simple way to stand up a REST API from a local JSON file (often used as a mock server for development/testing). It supports common CRUD patterns and additional JSON-server features such as filtering and routing based on the contents/structure of the JSON data.

50

mcp-server-computer

Provides an MCP server (stdio mode) that exposes a tool (queryConfig) to query local computer/system configuration: OS details, user information, Java runtime version, and platform-specific hardware/system info on Windows/macOS/Linux by executing relevant system commands.

MCP

50

postgresql-mcp-server-by-cdata

Provides a local MCP (Model Context Protocol) server that exposes data from a PostgreSQL database via CData JDBC Driver as MCP tools, primarily for reading (tables/columns) and running SELECT queries over stdio to an MCP client like Claude Desktop. It is configured by building a JAR and providing a JDBC connection .prp file.

MCP

50

spring-demo-mcp-server-sse

Spring Boot demo that exposes a simple UserService both as REST endpoints and as MCP tools over an SSE session endpoint, with JSON-RPC messages sent to a per-session messages endpoint.

MCP

50

temple-bridge

Temple Bridge is a local MCP (Model Context Protocol) server that exposes tool-based access (8 tools, 3 resources) for an LLM-based workflow. It appears designed to connect an "Action Layer" repository (back-to-the-basics) with a "Governance/Memory" repository (threshold-protocols), using middleware to maintain state across MCP tool calls and a human-in-the-loop approval gate for command execution.

MCP

50

json-server is a development tool that serves a full fake REST API from a local JSON file (or multiple files) by exposing typical CRUD endpoints for your data.

50

ones-wiki-mcp-server

Provides an MCP (Model Context Protocol) server implemented with Spring Boot that authenticates to an ONES platform instance, fetches Wiki page content from a provided Wiki URL, converts the HTML to an AI-friendly Markdown/text representation, and returns structured page content (headings, paragraphs, lists, tables, images/links).

MCP

50

pal-mcp-server-ramarivera

PAL MCP is a Python-based Model Context Protocol (MCP) server that provides a provider abstraction layer for orchestrating multiple AI model backends (e.g., Gemini, OpenAI, Anthropic, Azure, Grok, OpenRouter, local Ollama) and exposes multiple agentic “tools”/workflows (chat/thinkdeep/planner/consensus/codereview/precommit/debug, etc.). It also includes a CLI-to-CLI bridge tool (“clink”) to integrate external AI CLIs into workflows and to spawn isolated “subagents” within an existing CLI context.

MCP

50

review-flow

reviewflow is an npm CLI/server that automates AI code reviews for GitHub PRs and GitLab merge requests. It receives webhook events, queues and deduplicates review jobs, runs multi-agent Claude Code reviews, reports structured progress via an MCP server, streams live status to a WebSocket dashboard, posts review results to the MR/PR, and performs follow-up reviews after fix pushes.

MCP

50

terminal-mcp

terminal-mcp (tmcp) is a minimal terminal CLI client for Model Context Protocol (MCP) servers. It can connect to MCP servers via stdio (local) or via streamable HTTP (remote), discover tools from configured servers, generate a tools.json allowlist, and let agents list and call only enabled tools via terminal commands.

50

gitagent provides a git-native, framework-agnostic standard for defining AI agents as repository artifacts (primarily agent.yaml and SOUL.md) plus optional supporting files (skills, tools, workflows, memory, hooks, compliance). It includes a CLI to scaffold, validate, inspect, export/import adapters, install git-based dependencies, run agents from a repo, and generate audits; adapters map the identity/config to target frameworks or formats such as system prompts and Claude Code-compatible configs.

48

favicon-mcp-server

Provides an MCP server (implemented in Go) that converts provided SVG input into favicon assets in ICO and/or PNG formats (e.g., 16x16, 32x32, 48x48). Output is returned as base64 in MCP responses and can optionally be written to files on disk.

MCP

48

mcpapp-colorpicker

Provides a .NET Model Context Protocol (MCP) App with an interactive HTML color picker UI. Exposes an HTTP MCP endpoint at /mcp and a UI/resource endpoint for rendering the picker, with a tool named ColorPicker that accepts an optional initialColor (hex) and returns a result containing the UI resource URI to display.

MCP

48

mcp-interviewer

mcp-interviewer is a Python CLI (and library) that interviews an MCP server by running it (typically via an external command), performing constraint checking on tool metadata/capabilities, optionally running functional tests by invoking tools using an OpenAI-compatible chat completions client, optionally performing experimental LLM-based evaluations/judging, and generating a Markdown + JSON report with collected statistics and results.

48

termlink

termLink is an MCP server that exposes local terminal/shell execution, filesystem operations (read/write/list), directory existence checks, and process/environment introspection (e.g., process info, list processes, get_env) to an MCP client such as Claude Desktop.

MCP

48

CLI/Python “Claude Code skill” that helps create PlantUML diagrams from text, convert .puml/.md content into PNG/SVG images, validate PlantUML syntax, and support extracting/embedding diagrams from markdown workflows.

47

aci

ACI.dev is an open-source platform for unifying “tool-calling” in agentic IDEs/custom agents. It provides multi-tenant authentication, dynamic tool discovery, and intent/natural-language permission boundaries, exposed either via a unified MCP server (in a separate repo) and/or through SDKs (Python/TypeScript).

MCP

47

mcp-ssh

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.

MCP

47

model-context-protocol-resources

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.).

MCP

47

leanmcp-sdk

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.

MCP

47

repl-scratchpad

Provides a persistent Python REPL for coding agents using a tmux-backed session so variables persist across turns. Agents write Python code to a temp file; only print() output is intended to be emitted back to the conversation context, while intermediate data stays in the REPL session.

47

mcp-server-factory

mcp-server-factory is a Java (Spring Framework, not Spring Boot) MCP (Model Context Protocol) server intended as a learning tool and reference implementation. It exposes MCP tools/resources/prompts that help explain MCP concepts and generate task-planning checklists for common development activities (e.g., code cleanup, feature implementation, local MCP deployment).

MCP

46

open_api_to_mcp_server

Provides an MCP server that dynamically generates MCP tools from an uploaded OpenAPI (Swagger) specification and exposes them over both HTTP and stdio. It also supports calling OpenAPI operations via a /mcp HTTP endpoint, mapping operationId names to generated tools.

MCP

46

Callable-to-openai-function-calling-template

A Python utility that converts a user-defined Python function (using a specific docstring template and type annotations) into an OpenAI tool-calling compatible JSON schema/representation (function or tool format).

46

gitea-mcp-server

Provides an MCP (Model Context Protocol) server that lets an AI agent interact with Gitea (repositories, issues, pull requests, etc.) via MCP tools, so the agent can perform common repository management and information retrieval tasks.

MCP

46

Token Optimizer is a local (external Python) tool/plugin that audits and reduces “ghost tokens” in Claude Code / OpenClaw sessions by measuring context degradation, detecting wasted/duplicate content, tracking compaction loss, and providing checkpoint/restore and archival tooling for tool results.

46

utcp-mcp

UTCP-MCP Bridge provides an MCP server that exposes UTCP “manuals” as MCP tools. It can be run via npx (no install step for the user) and is configured through a .utcp_config.json to register HTTP/OpenAPI-based tools, post-process tool outputs, and manage tool discovery/execution from an MCP client (e.g., Claude Desktop).

MCP

46

css-noop-checker

Chrome DevTools extension (and MCP tool server) that detects CSS declarations that have no visible effect on the selected DOM element or across the full page. It uses computed styles plus heuristics, and reports actionable warnings with fix suggestions. The MCP server exposes the rules engine for AI-assisted analysis using Playwright.

MCP

46

DevDocs

DevDocs is a self-hostable documentation crawler and extraction tool that can crawl developer documentation sites (with depth control and link discovery), extract cleaned content, and expose it via an MCP server for LLM querying. It also provides a local UI and backend services via Docker, and supports exporting crawl results (e.g., MD/JSON) for further use.

MCP Free tier

46

mcp-breach-to-fix-labs

Provides a Dockerized set of Model Context Protocol (MCP) security lab servers with intentionally vulnerable and corresponding hardened implementations for multiple common vulnerability classes (e.g., path traversal, SQL injection, prompt/tool-response injection, command injection). Includes challenge walkthroughs and proof artifacts meant to reproduce exploit-to-mitigation flows end-to-end.

MCP

46

passage-of-time-mcp

Provides an MCP server (FastMCP-based) exposing time-related tools for LLMs: current datetime, timestamp parsing, time differences/since, contextual time-of-day/weekend/business hours, adding time, and formatting durations. Runs an SSE transport endpoint.

MCP

44

live-server

live-server is a local development utility that serves a project directory over HTTP and automatically reloads/broadcasts changes to the browser when files are edited.

44

A packaged “agent skill” that helps AI coding agents generate and maintain AGENTS.md files (and optional scoped subsystem variants) according to the agents.md specification. It includes scripts/templates for detecting project structure and stack signals and then producing/updating the agent context files idempotently with managed headers.

43

Custom-MCP-Server

Provides a Python-based Model Context Protocol (MCP) server exposing tools to scrape social media profile data (LinkedIn, Facebook, Instagram) and perform Google search via Serper/Google search. It is intended to be run locally (e.g., with Claude Desktop) and uses external APIs (RapidAPI and Serper) authenticated via environment variables.

MCP

43

Agent Skills Hub appears to be a web app and API that periodically syncs GitHub repositories, cleans/deduplicates and classifies them, computes multi-dimensional quality scores (including an “Agent Readiness” dimension), stores results in Supabase, and serves listings, trending/rising/top-rated views, RSS/sitemap, plus endpoints for submitting skills and subscribing to a newsletter.

42

Swag is a code-generation utility (commonly for Go) that parses API definitions (e.g., annotations/metadata) and generates Swagger/OpenAPI documentation artifacts for your service.

42

ubox-mcp-server

MCP server package ("ubox-mcp-server") intended to expose some "ubox"-related functionality to AI agents via the Model Context Protocol (MCP).

MCP

42

vscode-context-mcp

Provides a Model Context Protocol (MCP) server/extension to expose VS Code context (active files, tabs, diagnostics, terminal output) and enable controlled filesystem and shell command operations to AI assistants.

MCP

42

kiro-powers

A collection of “Kiro Powers” that provides curated templates and guidance for building Model Context Protocol (MCP) servers (via FastMCP/stdio), plus starter patterns for React apps using AWS Cloudscape Design System and Raycast extensions. The repo is primarily a set of installable “powers”/steering files rather than a single standalone API service.

42

mock-http-server

mock-http-server is a utility for standing up a local/mock HTTP server that simulates API responses for development and testing purposes.

42

cli

@smithery/cli is a Node/NPX command-line tool that lets you authenticate to Smithery, search/add/list/remove MCP server connections, browse MCP tools, install/score “skills” from a Smithery registry, and mint OAuth/service tokens.

MCP

42

install-mcp

CLI tool to install and manage MCP servers for multiple clients (e.g., Claude Desktop, Cursor, VSCode, etc.). Supports installing from package names, scoped packages, full command strings, and remote URLs; can perform OAuth-based authentication for remote servers and write generated configuration for the selected client(s).

42

A Java/Spring AI example that provides an MCP server image intended to be run as a local MCP tool for clients (e.g., Claude Desktop or VS Code). The README describes building a Docker image and configuring an MCP client to invoke the server’s tools.

MCP

40

openclaw-superpowers

openclaw-superpowers is a plug-and-play skill library for the OpenClaw persistent AI agent runtime. It provides a large set of predefined “skills” (core methodology, OpenClaw-native persistent/cron workflows, and security guardrails) plus companion scripts and an install script that symlinks skills, initializes local state directories, and registers cron jobs. It also describes agent abilities to self-modify by writing new skills during conversation via a create-skill mechanism.

40

velocity

Velocity is a local-first web app (Next.js + Bun) that acts as a command center for AI coding CLIs (Claude Code, Codex CLI, Gemini CLI). It runs and inspects coding sessions, captures analytics (usage/cost/latency/tools/routing context), and helps turn repeated patterns into reusable agents/workflows/skills/commands, including routing visualization. It also supports MCP (via the @modelcontextprotocol/sdk dependency) as part of its build layer surfaces.

40

Agent-guardrails is a shell-based toolkit that installs and wires mechanical enforcement for AI coding agents via git pre-commit hooks and local validation scripts. It helps prevent common bypass patterns and hardcoded secret leaks, and encourages an import-based “registry” pattern (via a project __init__.py template) so new code imports validated functions rather than reimplementing them.

40

Nuitka is a Python compiler that translates Python code into generated C/C++ code and then into an executable or extension module, producing binaries that run compatibly with CPython behavior (with options for different packaging modes like standalone/onefile).

39

unirt.amplify-doc-mcp-server

unirt.amplify-doc-mcp-server appears to provide an MCP server that exposes “Amplify docs” related content/operations to an AI agent. This package is intended to be used through an MCP-compatible host so the agent can query or retrieve Amplify documentation resources in a tool-call workflow.

MCP

39

wuwa-mcp-server

A community MCP server package intended to be run as an MCP (Model Context Protocol) server, exposing tools to an MCP-capable agent. This evaluation is limited because no README/repo metadata or manifest content was provided to verify what tools it implements, configuration options, or operational behavior.

MCP

39

mcp-filesystem-server

mcp-filesystem-server is a Go implementation of an MCP (Model Context Protocol) server that exposes filesystem access to an MCP-capable client (e.g., Claude Desktop) with a configured allowlist of directories.

MCP

39

portone-mcp-server

MCP server wrapper for PortOne (portone-mcp-server), exposing PortOne-related functionality to AI agents via the Model Context Protocol.

MCP

39

@portkey-ai/hoot is an MCP (Model Context Protocol) testing tool with a browser UI. It connects to MCP servers (HTTP and SSE), helps test/execute tools with parameters, supports OAuth 2.1 authentication flows, and persists server/tool configuration and (on local runs) OAuth tokens in a local SQLite database. It can be run instantly via hoot.run or locally via npx/npm.

37

Provides a Claude Code/OpenClaw/SkillsMP “skill” that uses natural-language descriptions to generate Excalidraw diagram JSON and export it to PNG/SVG (PNG via a local CLI; SVG via Kroki API). It also includes design conventions (layout modes, spacing rules, semantic colors, arrow styles) and supports exporting/editing via .excalidraw files.

37

pointr-cloud-v8-mcp-server

An MCP server package (pointr-cloud-v8) intended to expose Pointr Cloud v8 capabilities to LLM/agent runtimes via the Model Context Protocol, enabling agents to call Pointr-related actions as MCP tools.

MCP

37

Runs Apache JMeter in a Docker container to execute load/performance test plans, typically by mounting JMX test files and running the JMeter CLI in batch mode.

36

A Claude Code “skill” that generates, audits, and converts software documentation. It supports greenfield template-based documents (e.g., SRS/PRD/SDD/OpenAPI/user guides), brownfield reverse-engineering for certain frameworks (notably Spring Boot and Pulumi), documentation audits with gap analysis/checklists, and diagram generation (via other skills). It also uses a “Progressive Disclosure Architecture (PDA)” approach described as loading only the core routing content by default and pulling workflow/templates on demand.

36

mcp-server-bruno

mcp-server-bruno is an MCP server package intended to integrate Bruno (an API testing/client tool) resources or capabilities into an agent via the Model Context Protocol (MCP).

MCP

36

tcpping-mcp-server

tcpping-mcp-server is an MCP server intended to perform TCP reachability checks (“ping” over TCP) to specified hosts/ports, exposing the functionality to AI agents via the Model Context Protocol.

MCP

36

ybl-mcp-server

ybl-mcp-server is an MCP server package intended to expose tools/resources to AI agents via the Model Context Protocol, likely backed by YBL-related capabilities. From the provided input, no README/repo manifest details are available, so tool coverage, parameters, and operational behavior cannot be verified.

MCP

36

skill-forge is a local Python CLI/repo scaffolding tool that designs, builds, reviews, evolves, publishes, evaluates, benchmarks, and converts “Claude Code” Agent Skills (per the Agent Skills open standard). It generates skill file trees, scripts, templates, orchestrator/sub-skill structures, and supports conversion to other tooling ecosystems.

36

xiyan-table-mcp-server

A Model Context Protocol (MCP) server intended to expose "xiyan-table"-related table functionality to MCP-capable agents via defined MCP tools/resources.

MCP

36

mTarsier is an open-source desktop/CLI app for managing MCP servers and connecting them to multiple AI clients (e.g., Claude Desktop, Cursor, VS Code) by reading/editing client MCP configuration files, offering a dashboard/marketplace, and performing config backups/rollback.

34

mcp-go-sdk

A Go SDK implementing the Model Context Protocol (MCP), providing building blocks to create MCP servers (tool/resource/prompt registration and execution) and to communicate with MCP clients over multiple transports (stdio, SSE, WebSocket).

MCP

34

playwright-bot-bypass

playwright-bot-bypass is positioned as an automation skill that uses stealth browser variants (rebrowser-playwright / undetected-chromedriver) and example scripts/templates to reduce detection signals (e.g., removing webdriver exposure) to make web automation and scraping more likely to work without CAPTCHA/login.

34

claude-code_rails-upgrade-skill

Provides a Claude Code skill that assists with upgrading Ruby on Rails applications between versions by generating detection scripts, upgrade reports (with code examples), and previews of `rails app:update` configuration changes, using a sequential (no-skips) upgrade strategy and advising a dual-boot approach.

34

http-server is a simple static HTTP server for serving files from a local directory (and optionally directory listings). It is typically used as a lightweight way to host a folder for development, testing, or quick demos.

34

marketing-skill-pack

A one-command installer for an “AI Marketing Hub” suite: clones/updates several Claude Code-related repos, installs their skills, and downloads a WordPress plugin (WP MCP Ultimate) for MCP-based WordPress abilities.

34

mcp-server

A small set of MCP server binaries (configured via stdio) that provide tools for specific tasks: text-to-SQL against a MySQL database, retrieving from a Dify knowledge base/dataset, and performing data conversion via a separate command.

MCP

34

awesome-agent-skills is a curated directory/repository of “Agent Skills” resources, tutorials, and pointers to many skill projects and ecosystems (e.g., Claude/ChatGPT skill usage patterns and third-party skill stores/harnesses). It describes a standard on-disk structure for skills (SKILL.md with optional references/scripts/assets) and provides guidance for discovering/adding/updating skills via CLI tools for different environments.

33

Continuous-Claude-v3

Continuous Claude is a local Python-based “Claude Code” extension that aims to provide persistent, token-efficient context across sessions using a memory system, continuity/ledger handoffs (YAML), and multiple specialized agents and skills. It also claims to reduce token usage via TLDR multi-layer code analysis and indexing, and to improve code-quality via shift-left validation (e.g., ruff/pyright) after edits.

33

A Java-based MCP (Model Context Protocol) server project intended to dynamically expose OpenAPI definitions as MCP tools for consumption by LLMs via an MCP client. The provided metadata does not confirm runtime behavior, but describes a Spring OpenAPI-to-MCP bridge.

32

MCP_SERVER_JAVA

Provides a Java implementation of an MCP (Model Context Protocol) server with a set of example tools (math, greeting, time) and an ai_chat tool that forwards prompts to an Azure AI Foundry/Azure OpenAI-style backend. It can be run as an HTTP server (localhost) and appears intended for MCP client integrations (e.g., Claude Desktop, VS Code MCP).

MCP

32

restapi-mcp-server

MCP server package that exposes REST API capabilities to an MCP-compatible AI agent by wrapping/bridging REST endpoints as MCP tools. (Evaluation is based only on the provided package name; no README/repo metadata or manifest content was supplied.)

MCP

32

strayl-mcp-server

strayl-mcp-server appears to be an MCP (Model Context Protocol) server package intended to expose one or more capabilities to AI agents via MCP. However, no README/repo/package-manifest content was provided in the prompt, so the exact tools, inputs/outputs, and operational details cannot be verified from available data.

MCP

32

youtube-dl-server provides a service/API wrapper for youtube-dl (and related tools) to fetch and/or process media from YouTube and other supported sites via a server interface.

32

yu-terms-mcp-server

An MCP server package intended to expose Yu terms-related capabilities to an AI agent via the Model Context Protocol (MCP). Specific tools, endpoints, authentication, and behaviors are not provided in the supplied data.

MCP

32

puli-mcp-server

puli-mcp-server is an MCP (Model Context Protocol) server package intended to expose capabilities to AI agents via the MCP interface. Based on the name alone and without README/repo details, the exact tools and behaviors cannot be verified.

MCP

32

tdd-mcp-server

tdd-mcp-server is an MCP (Model Context Protocol) server intended to help with Test-Driven Development workflows by exposing MCP tools/resources that agents can call.

MCP

32

An all-in-one documentation/guide repository for Claude Code: how to set it up, use its CLI features (slash commands, hooks, workflows, skills), and integrate with MCP servers and related tooling.

32

A simple TCP echo server: it listens for TCP connections and echoes back received data to the client. Typically used for testing network connectivity, framing, and client/server behavior.

32

tcp-echo-server

tcp-echo-server is a simple TCP server that accepts socket connections and echoes received data back to the client (useful for testing connectivity and basic networking behavior).

32

thordata-mcp-server

An MCP server package (thordata-mcp-server) intended to expose tools/data via the Model Context Protocol, enabling an AI agent to call server-provided capabilities through MCP.

MCP

32

zed-mcp-server-miaoduo

A Zed editor MCP server extension intended to integrate with miaoduo’s MCP server package (@miaoduo/miaoduo-mcp-server). The provided README and metadata describe the integration at a high level, but do not include concrete usage, configuration, or API surface details.

32

docker-compose-generator

docker-compose-generator is a utility that helps generate Docker Compose configurations (typically by templating/assembling service definitions into a docker-compose.yml) rather than requiring users to author the full compose file manually.

31

CLI + AI coding-tool “skills” that scan a codebase and generate human-readable architecture documentation with Mermaid diagrams, organized into a filesystem tree under `.omm/`. Optionally can link/push the generated architecture to a private cloud for sharing/viewing.

31

simple-time-mcp-server

A minimal MCP server for exposing simple time-related functionality to AI agents (e.g., retrieving current time/date and related utilities) via the Model Context Protocol.

MCP

31

utility-mcp-server

MCP server package (utility-mcp-server) intended to expose “utility” capabilities to AI agents via the Model Context Protocol. Specific tools/endpoints, configuration, and behavior were not provided in the input, so exact functionality cannot be verified.

MCP

31

bitbucket-server is an integration package for Bitbucket Server (self-hosted Bitbucket Data Center). It provides programmatic access to Bitbucket resources (e.g., projects/repositories, commits, pull requests, build-related data depending on installed plugins/APIs) so other tools/agents can automate Git workflow and repository management against a Bitbucket Server instance.

30

echo-server

echo-server is a simple server that echoes back received input (commonly used as a minimal example for building/testing network services).

30

echo-server

echo-server is a basic echo service intended to accept input over a network interface and return the same content back to the caller (useful for testing connectivity and client/server wiring).

30

ddev-webserver is the webserver component/container used by DDEV for local development. It provides the HTTP(S) serving layer for a DDEV project, wiring requests to the app runtime container(s) and handling common local webserver concerns (routing, ports, TLS options as supported by the overall DDEV stack).

30

share-best-mcp appears to be an aggregator/curation repo ("Share Best MCP Servers") that crawls and analyzes MCP server repositories and publishes a categorized list (and points to a web search site). It does not, by itself, define a single MCP server interface for clients; instead, it provides scripts and content to discover other MCP servers and filter them by a score threshold (>= 85).

29

xhs-bailian-mcp-server-zhulong

xhs-bailian-mcp-server-zhulong is an MCP (Model Context Protocol) server package intended to expose “bailian/zhulong” capabilities/tools to an MCP-capable agent runtime. Based on the provided package name alone, exact tools and behaviors cannot be verified from source/README contents in this prompt.

MCP

29

zsb-mcp-server

An MCP (Model Context Protocol) server implementation intended to expose tools/actions to MCP-compatible AI agents under the package name zsb-mcp-server.

MCP

29

echoserver

echoserver is a simple echo server: it accepts incoming network connections/requests and responds by echoing back received data (useful for local testing and verifying connectivity).

29

echo-server

echo-server appears to be a simple server that echoes back received input (a common example “echo” service). No repository/README contents were provided here, so interface details, auth, error behavior, and deployment guidance cannot be confirmed.

29

gpt2099.nu

A small SolidJS/Vite frontend UI prototype project (based on a Vite template) that runs a local web app at http://localhost:3000. The provided README does not describe any backend APIs or external integrations.

29

An MCP server intended to provide wallpaper-related functionality to AI agents via the Model Context Protocol, enabling an agent to discover/retrieve wallpaper images (exact capabilities not provided in the prompt).

29

syntect_server is a server wrapper around the Rust syntect syntax-highlighting library. It provides an HTTP service to generate syntax highlighting (e.g., converting code into highlighted output based on syntax definitions and themes).

28

tl-mcp-server

tl-mcp-server appears to be an MCP server package intended to expose tools/resources to an MCP-capable agent runtime. However, no README/repo metadata or manifest content was provided in the prompt, so concrete functionality, endpoints/tools, and operational behavior cannot be verified.

28

awesome-claude-code-plugins

This repository is an “awesome” curated index of Claude Code plugins, listing categories and links to individual plugin directories (e.g., slash commands, subagents, MCP servers, hooks). It also documents how to host and share a plugin marketplace via a Git repository and a .claude-plugin/marketplace.json file.

28

gemini-cli-desktop

Gemini CLI Desktop is a cross-platform desktop (Tauri) and web UI for interacting with Gemini CLI and Qwen Code. It provides visual confirmation for AI tool actions, real-time thought process display, code diff viewing, chat history management with search, a file tree browser and file @-mentions, and MCP server integration. It supports multiple models/providers and a multi-language UI.

28

MCP-Server-build-using-Spring-AI-and-Java

A Java/Spring Boot-based MCP (Model Context Protocol) server implementation built using Spring AI and Spring Data JPA. It is intended to expose application capabilities to MCP-capable AI agents, with persistence via JPA.

MCP

28

Spring Boot application intended to act as an MCP server for an “AI-powered dog adoption scheduling” service. Based on the provided README, it can be built and run as a Docker container exposing an HTTP service on port 8081 (or SERVER_PORT override).

28

awesome-mcp-servers is a curated directory/collection of links to Model Context Protocol (MCP) servers, organized by category. It does not itself provide an MCP server, API, SDK, or executable integration—its function is to point users to other MCP server implementations.

28

cocube-mcp-server

An MCP (Model Context Protocol) server intended to connect an AI programming robot (“CoCube”) to external capabilities via an MCP interface, backed by a Rust dependency (“cocube-rs”) referenced from another repository for documentation.

MCP

28

spingai-mcp-server

spingai-mcp-server is an MCP server package (as indicated by its name) intended to expose tools/resources for AI agents via the Model Context Protocol. The provided input contains only repository metadata (no README/code, API surface, auth, or docs), so the exact MCP tools and behavior cannot be verified.

MCP

27

zmy-mcp-server

An MCP (Model Context Protocol) server package intended to be used by LLM agents to access some external capability(s). The provided prompt includes only the package name and no README/repo content, so the specific tools/endpoints and behavior cannot be verified.

MCP

27

echoserver-udp

An example UDP echo server that listens for UDP datagrams and sends the received payload back to the sender (useful for testing UDP connectivity).

27

mcp-server-test

This appears to be an MCP (Model Context Protocol) server launched as a Java JAR with stdio transport enabled (via a Spring AI MCP server JVM property). No further functionality, tools, or protocol details are provided in the supplied materials.

MCP

27

pipeiq-explorium-mcp-server

MCP server package for exposing “pipeiq-explorium” functionality to AI agents via the Model Context Protocol (MCP).

27

code-server

code-server is a self-hosted way to run Visual Studio Code in the browser, typically by proxying VS Code’s web UI and wiring it to a backend that runs the editor environment (including extensions) on your server.

27

A Claude Code skill/command that helps organize personal tax documents (PDFs, spreadsheets, W-2s/1099s, receipts) into a year-based folder structure, classifies documents into tax categories, and generates accountant-ready CSV draft reports (e.g., Schedule E, W-2/1099 summaries, donations, business trip expense comparisons).

27

FlyEnv

FlyEnv is a cross-platform (Windows/macOS/Linux) local development environment manager that installs and runs common developer services natively (without Docker), including web servers (Apache/Nginx/Caddy/Tomcat), language runtimes (e.g., PHP with Composer, Node.js, Python, Java), and supporting services (e.g., MySQL/PostgreSQL/MongoDB/Redis/RabbitMQ/Elasticsearch/Mailpit). It also provides features like local domains/SSL, config/log editing, port management, and per-project version switching.

26

Awesome-MCP is a curated directory/README of Model Context Protocol (MCP) ecosystem resources, including MCP servers, clients, SDKs, and related tools. It is not itself an MCP server, API, or SDK for making requests.

26

mcp-go-server

A Go-based MCP (Model Context Protocol) server implementation/library intended to expose tools/resources to an MCP-compatible client/host.

MCP

26

pymcp-template

pymcp-template appears to be a template project for building an MCP (Model Context Protocol) server/tooling in Python. No repository content was provided here beyond the package name, so specifics (tools exposed, transport, endpoints, auth) cannot be verified.

26

cp-server-connect-datagen appears to be a data-generation utility for a “server connect” control-plane (likely used to produce synthetic data/events for local development or testing). However, no README/repo/package manifest content was provided in the prompt, so the exact functionality, interfaces, and operational behavior cannot be verified.

24

echoserver

A minimal echo server that listens on a TCP/HTTP endpoint and returns received request data (commonly echoing the request body or message back to the caller). Intended as a simple example or test server for connectivity and basic request/response behavior.

24

code-server

code-server runs VS Code (web version) in your browser by hosting the editor on a machine and tunneling access over HTTP(S). It provides a web-based IDE backed by your local filesystem and configurable extensions.

24

code-server

code-server provides a self-hosted web interface for running VS Code in the browser (remote development) with access to a local workspace on the host system.

24

springboot-mcp-server

A Spring Boot-based MCP server framework/service intended to expose functionality via an MCP interface, with a RESTful backend indicated by the repo description. The README only provides minimal requirements (JDK 17+) and a note to replace a DeepSeek API key in source code, but does not describe available tools or endpoints.

MCP

24

code-server is a self-hosted (or deployment-provided) web-based VS Code experience: it runs the VS Code editor in a browser, serving an HTTP(S) interface that lets users edit files, run terminals/tasks, and access projects from a remote environment.

24

skills

A monorepo of reusable, self-contained “skills” intended for use with Codex/Claude-style agents. The README lists multiple skills including: detecting which biomedical claims in Markdown need citations (cite-them-all), generating structured medical lecture materials including references (academic-lectures), processing Gmail invoice emails into structured summaries (gmail-invoice-processor), and converting Markdown into Xiaohongshu (RedNote) image card assets while preserving structure and local images (md-to-xhs-cards).

23

skills

Provides an archived collection of “skills” backed up from clawdhub.com. The README frames the repository as a historical archive rather than an actively maintained, fully supported service.

23

awesome-agentic-advertising

This repository is an “awesome” curated directory of resources for AI-agentic advertising. It links to MCP servers, protocols/standards, creative-generation models, conversion tracking APIs, and agent frameworks, but it is not itself a single runnable API/service.

23

wx-mcp-server-test appears to be an MCP server package intended for testing/development of MCP tooling and agent integrations. Based on the provided information, no functional description, endpoints/tools, or configuration details were included, so the exact behavior cannot be verified.

22

chatgpt-ui-wsgi-server

Wsgi server for chatgpt-ui (a web UI). It provides a Python WSGI-compatible deployment wrapper so the chat UI can be served behind a WSGI application server (e.g., Gunicorn/uWSGI) and proxied by a reverse proxy.

21

code-server-python

code-server (Python package) provides a web-based VS Code environment (“code-server”) that can run on a machine and be accessed via a browser, enabling remote editing/development. The Python package typically wraps/downloads/distributes code-server rather than implementing a separate API service.

21

mcp-server-springboot

Undocumented from the provided data. The name suggests it is an MCP server implementation for a Spring Boot application, but no repository README, code, or manifest was provided to confirm capabilities, endpoints, tools, configuration, or behavior.

21

sonarqube-mcp-server

A Model Context Protocol (MCP) server project intended to connect LLM agents to SonarQube/SonarCloud functionality. Based on provided README/repo metadata, the repository is archived and indicates it is no longer maintained.

DR-ServerMCP

DR-ServerMCP appears to be a Go-based project intended to provide an MCP (Model Context Protocol) server interface, likely exposing some “DR” functionality to agent tooling. However, no repository contents (README, API specs, MCP tool definitions, auth, or error/rate-limit behavior) were provided, so concrete capabilities cannot be verified from the given data.

20

fpl-mcp-server

MCP server intended to provide Fantasy Premier League (FPL) data/actions via the Model Context Protocol. The provided README contains only a title with no implementation or usage details.

MCP

20

spring-ai-mcp-server-sse

pycharm

pycharm is a JetBrains integrated development environment (IDE) for Python (and other languages) providing code editing, navigation, refactoring, debugging, and project tooling.

Insufficient information provided to evaluate the gmod package. No README/repo metadata or manifest details were included, so interface, auth, pricing, and operational behavior cannot be determined from observable facts.

0

guacozy-server

0

hfish-server

No package content (README/repo metadata/manifest) was provided for hfish-server, so its functionality, interfaces, auth, pricing, and operational characteristics cannot be determined from the prompt.

0

hsl-map-server

Not enough repository/README/package-manifest content was provided to determine what hsl-map-server does, how it exposes functionality, or how it is operated.

0

hydra2

hydra2 is not sufficiently described in the provided input to evaluate its functionality. No README/repo manifest content was included, so interface, auth, pricing, and operational behavior cannot be determined from observable facts.

0

Insufficient information provided to evaluate this package. The only input is the package name (xmcp-server-exepython) without README/repo contents or configuration/manifest details.

0

Z.ai2api

No package content (README/repo metadata/manifest) was provided for Z.ai2api, so its API surface, authentication, pricing, and operational behavior cannot be assessed from evidence.

0