MCP Clients

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.

📄 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.

The official Ruby SDK for the Model Context Protocol servers and clients.

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

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

Agent samples built using the Strands Agents SDK.

MCP Tools for Obsidian enables AI applications like Claude Desktop to securely access and work with your Obsidian vault through the Model Context Protocol. The plugin adds MCP capabilities and

A minimalistic MCP client with a good feature set.

Ollama MCP client: TUI for managing local LLMs. Multi-server, streaming, tool management, & full model config. Dev-focused.

MCP memory server for AI coding assistants. Works with Claude Code, Cursor, Codex, Gemini CLI, Cline, Continue, Cherry Studio, Zed, Hermes, OpenClaw, and any MCP client. Local, encrypted, verbatim recall. MIT.

Native macOS client for Model Context Protocol (MCP)

This repository provides a Model Context Protocol (MCP) tool enabling Claude to interact with the ChatGPT desktop app on macOS, allowing users to ask questions, view history, and continue conversations.