Browse and discover Model Context Protocol compatible clients.
The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% wall time, 0 losses across 96 tasks on Claude Opus 4.7. Structural code navigation + persistent memory. Works with every MCP client.
Chatmcp is a cross-platform AI chat client for MacOS, Windows, Linux, iOS, and Android, allowing users to chat with an MCP server after configuring their LLM API key and endpoint
Minima is an open-source RAG platform offering on-premises containerized solutions, integrating with ChatGPT and MCP, or operating fully locally. It enables secure querying of local documents using various LLMs.
QGISMCP integrates QGIS with Claude AI via the Model Context Protocol, enabling Claude to control QGIS for tasks like project creation, layer manipulation, and code execution. It uses a QGIS
This repository provides an Arduino library for interfacing with the MCP2515 CAN controller, enabling CAN-BUS communication for Arduino projects. It supports standard and extended frames, along with sending, receiving, and
CLI MCP package manager & registry for all platforms and all clients. Search & configure MCP servers. Advanced Router & Profile features.
Arcade Python SDK, CLI, and toolkits
MCP-Bridge bridges the OpenAI API and MCP tools, enabling developers to use MCP tools through the OpenAI API interface. It supports chat completions, MCP tools, and offers an SSE Bridge
AgentKit enables building multi-agent networks with deterministic routing and rich tooling via MCP, supporting TypeScript AI developers with fault-tolerant cloud deployment. It offers flexible routing, multiple model providers, and built-in tracing.
A library for communication with a Minecraft client/server.
A secure local sandbox to run LLM-generated code using Apple containers
VectorCode is a tool that indexes code repositories to help users write better prompts for coding LLMs by providing project context. It includes a neovim plugin and uses Chromadb as
📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.
Simple, modular, and observable Go framework for backend applications.
Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents