ACI.dev is an open-source AI agent tool infrastructure that provides multi-tenant authentication, permission management, and dynamic discovery functions for over 600 pre-integrated tools. It supports calls through a unified MCP Server or a lightweight SDK, simplifying the development of production-level AI agents.

A local server based on the MCP protocol that implements semantic search and RAG functions for Apple Notes, which can be called by AI assistants such as Claude.

Pipelock is an open-source AI agent firewall that provides security protection with zero runtime dependencies through a single binary file. It adopts an architecture with separated capabilities and deploys a nine-layer scanning pipeline between the agent and the Internet to prevent secret leakage, prompt injection, and malicious tool calls. It supports multiple proxy modes (Fetch proxy, forward proxy, WebSocket proxy) and MCP proxy, and provides functions such as an emergency stop switch, audit logs, and SIEM integration.

Arbor is a locally prioritized codebase impact analysis engine that accurately tracks function calls, imports, and inheritance relationships by building a semantic dependency graph, helping developers understand the actual impact scope of changes before refactoring.

MCP2Lambda is an MCP protocol server that runs AWS Lambda functions as tools for large language models (LLMs). AI models can call Lambda functions to access private resources and AWS services without code modification.

This project is an MCP client based on LangChain, used to demonstrate how to call MCP server tools through the LangChain ReAct Agent. It supports the LLMs of Anthropic, OpenAI, and Groq and provides the function of converting MCP tools to LangChain tools.

The Linkup MCP Server is a tool used to integrate Linkup's web search functionality with AI models supporting function calls through the MCP protocol.

Janee is an AI agent key management tool based on the MCP protocol. It securely stores and injects API keys as an intermediary, enabling agents to call services without touching the original keys. It also provides complete audit logs, access policy control, and session management functions.

This is an MCP server project for GitHub Advanced Security (GHAS), used to call the security scanning functions of GitHub repositories through the MCP protocol, including dependency alerts, secret scanning alerts, and code scanning alerts. It supports authentication through GitHub CLI or a personal access token and provides an installation method for the VS Code extension.

An MCP server that enables AI assistants to interact with the Ulysses writing app on macOS through the x - callback - url API, providing functions such as document creation, content management, navigation, and metadata operations.

An MCP server that can automatically convert the project's npm scripts into tools that can be called by the AI assistant. It supports npm, pnpm, yarn, and bun, and provides security configuration and automatic detection functions.

The Infisical Model Context Protocol (MCP) is a service protocol that integrates with the Infisical API through function calls. It supports multiple tool operations such as creating, deleting, and updating keys, and provides a debugging tool called MCP Inspector.

AgentRPC is a general - purpose RPC layer for connecting function calls of AI agents across network and language boundaries.

Didlogic MCP Server is a model context protocol server that implements the Didlogic API, providing a standardized interface for large language models to access Didlogic services, including balance management, SIP account management, call record query, and other functions.

This project is a Python - based implementation of the MCP (Model Context Protocol) server and client, aiming to provide standardized interfaces for AI models, unify the tool call formats of different large - model vendors, and integrate document search functions for multiple AI frameworks.

Magic-API MCP Server is a model context protocol server designed specifically for Magic-API development, providing a complete development toolchain, including documentation query, API call, resource management, debugging, and backup functions, to help developers efficiently build and manage Magic-API interfaces.

The MCP Proxy Sidecar is an enhanced JetBrains MCP server with WebSocket monitoring functionality, supporting real - time viewing of tool call situations.

This project provides code analysis and editing capabilities through the LSP protocol, supports MCP tool calls for TypeScript/JavaScript, includes functions such as file operations, symbol lookup, and error checking, and has security features such as path restrictions.

Bookworm is a toolset for processing docs.rs documentation, including functions such as downloading, indexing, and querying documentation, and provides an MCP service interface for LLM calls.

An Asterisk - based voice - dialogue automated phone call MCP server that supports real - time voice - to - voice function and provides a complete phone automation solution.

OneTool is a unified MCP server that exposes over 100 tools through the Python API, significantly reducing token consumption and cost when AI calls tools, avoiding context pollution, and supporting multiple functions such as web search, database, file operations, and chart drawing.

An HTTP server based on the MCP protocol, providing AGENTS.md knowledge management, structured task tracking, version history recording, and scratchpad functions, supporting multi - user collaboration and AI sub - agent calls.

The Supabase MCP Server is a middleware that bridges MCP clients and Supabase services, providing comprehensive functions such as database operations, storage management, and edge function calls.

The MATLAB MCP Server project provides integration with MATLAB and supports creating and executing MATLAB scripts and functions through clients such as Claude.

The Feishu MCP Server is a service that implements the Model Context Protocol, supporting interaction with the Feishu API through tool calls and mainly providing Bitable operation functions.

An MCP server that allows Claude Desktop to directly call the ChatGPT API, supporting custom parameters and web search functions.

This project demonstrates how to use Google's Gemini 2.5 Pro model to interact with the flight search tool under the MCP protocol through the function call feature, enabling natural language queries for flight information and returning formatted results.

The VeChain MCP Server is an MCP server designed specifically for the VeChain network, providing advanced functions such as querying official documents, calling the Thor REST API, managing cryptocurrency wallets, and signing.

The MetaTool MCP Server is a proxy server used to connect multiple MCP servers and forward tool calls to the appropriate servers. It is used in conjunction with the metatool-app to provide GUI tool management functions. The project is deprecated, and the Node.js alternative version is recommended.

The official MCP server of MusicMCP.AI allows AI assistants (such as Claude) to call an advanced AI music generation platform through natural language instructions, supports song generation in inspiration mode and custom mode, and provides balance query and health check functions.

The CoinGecko Server is a project that provides an MCP service for cryptocurrency data interaction and an OpenAI function call interface.

The Gridly MCP Server is a server-side tool for managing Gridly API projects, providing functions such as project management, grid operations, and database management, and supporting calls through MCP clients such as Claude Desktop.

This project builds an HR chatbot based on RAG. The MCP server serves as the functional call center to implement PDF document upload, parsing, retrieval, and natural language question answering functions.

A lightweight Java-based MCP server used to connect to databases (such as Virtuoso) via JDBC, providing functions such as querying database structures, executing SQL/SPARQL queries, and calling stored procedures.

The Vapi MCP Server is a tool that integrates the Vapi API through function calls, supporting voice assistant calls and appointment management through Claude Desktop.

This is a Korean Public Data Portal OpenAPI integration tool based on the Model Context Protocol. It provides API search, document retrieval, and data call functions, simplifying the access process for Korean public data.

The Workers MCP Server is a proof-of-concept project that implements a Model Context Protocol (MCP) server through Cloudflare Workers, enabling MCP clients such as Claude Desktop to call the RPC functions of Cloudflare Workers to extend their capabilities. The project provides functions such as documentation generation, local proxy, and remote call, supporting developers to quickly build and deploy MCP services.

This project is a server for the Gemini model based on the MCP protocol, encapsulating Google's Gemini API and providing functions such as text generation, function calling, and file handling.

This project builds a RAG-based HR chatbot. Through the MCP server as the function call center, it realizes the functions of PDF document uploading, parsing, retrieval, and natural language Q&A.

The Kagi MCP Server is a tool integration service that provides search and summarization functions for Claude Desktop, supporting API calls to Kagi's search and summarization engines.