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.

This project is an integrated MCP server suite with various functions, including media tools, information retrieval, PDF generation, and presentation creation services, which need to be configured and run separately.

The MCP Server Logger is a tool used to solve the problem of console.log interfering with protocol communication in MCP server development. It keeps the communication pure by redirecting logs to a separate terminal.

FFmpeg-MCP is a model context protocol server designed to help LLMs process various multimedia content created by humans and machines, including functions such as decoding, encoding, transcoding, mixing, separating, streaming, filtering, and playing.

A modular and extensible MCP server template that provides clear architectural separation, a small and focused file structure, simple extension points, and comprehensive error handling.

The MCP Speaker Diarization and Recognition System is a complete solution integrating GPU-accelerated speaker separation, speech recognition, emotion detection, and a web interface. It combines the speaker separation of pyannote.audio with the faster-whisper transcription technology, supporting persistent speaker recognition (one-time registration, permanent recognition), dual-detector emotion analysis (combining general AI and personalized voiceprints), real-time stream processing, REST API, and MCP server, and is designed for AI intelligent agent integration and hobby projects.

Fluent MCP is a modern framework for building Model Context Protocol (MCP) servers with intelligent inference capabilities. It supports AI integration, tool separation, and offloading of complex inferences, and uses a dual - layer LLM architecture for efficient inference.

An MCP Server based on Playwright, focusing on automated end-to-end testing, leveraging LLM-driven test verification to separate testing from the client.

PictMCP is an MCP server that provides reliable and algorithmically correct pairwise test generation for software developers using AI assistants to design test cases. It runs Microsoft's PICT algorithm locally using WebAssembly, separating the AI's thinking from combinatorial mathematics calculations to ensure the determinacy and correctness of test generation.

This is an MCP server designed for the Base network, allowing blockchain operations to be performed through natural language commands, including wallet management, balance inquiry, and transaction execution. It supports the Base mainnet and the Sepolia testnet and can be integrated with LLM clients such as Claude Desktop.

A simple MCP server based on thirdweb that provides blockchain functions for LLM, supporting operations such as token deployment, minting, transfer, and balance query, and runs on the base sepolia network by default.

mcp-request is an MCP server tool used to quickly expose and reuse various HTTP APIs through the MCP protocol, avoiding the need to create a separate MCP server for each API and improving development efficiency.

The Model Context Protocol SDK is a standardized tool implemented in TypeScript for separating context provision from actual interaction in LLM interaction, supporting client and server development.

SQL MCP Server is a unified proxy interface that allows AI models to inspect, query, and interact with various types of databases (such as MySQL, SQL Server, Oracle, etc.) through a set of standardized toolsets, without the need to configure separate servers for each database.

A lightweight MCP server that enables cross-chain asset transfer between the Ethereum Sepolia testnet and the Monad testnet through the Wormhole bridge, supporting operations such as balance query and cross-chain transfers.