MCP Clients

MCPX4J is a Java client library for MCP.RUN, enabling developers to easily integrate and invoke installed tools using a simple API with features like installation caching and customizable JSON decoding.

This repository hosts a web-based MCP client for creating and managing advanced chatbot applications, integrating with backend MCP servers via SSE for real-time interaction and Dify for chatbot management.

mcpx-py is a Python library that enables interaction with various Large Language Models (LLMs) using mcp.run tools, supporting models from PydanticAI, OpenAI, Ollama, and Gemini. mcpx-py is a Python library

practical patterns for agentic coding: hooks, agents, automation. built from hundreds of claude code sessions

A Unity MCP server that allows MCP clients like Claude Desktop or Cursor to perform Unity Editor actions.

EasyMCP is a Python rewrite of the Model Context Protocol, offering features like server management, dynamic addition/removal, namespaced tools/resources, and automatic cache invalidation for efficient server interactions. EasyMCP is a

Desktop4mistral is a Python-based desktop application offering a user-friendly interface for interacting with Mistral AI models, featuring model selection, chat history, command support, and Markdown support. Desktop4mistral is a Python-based

Oneshot is an early-stage macOS client for Anthropic's MCP, allowing users to bring their own API key, discover tools, and install them with a single click. Oneshot is an early-stage

arXiv MCP Server Client 🐙 enables AI assistants to search, retrieve, analyze, and summarize arXiv papers with features like author/category browsing, trends, and citation insights.

Salesforce MCP Library is a local stdio bridge for Salesforce MCP endpoints using OAuth client credentials, featuring a reusable Apex MCP library and JSON-RPC 2.0 core.

This React-based demo showcases an MCP client interacting with SSE servers, enabling tool calls and text completion, though it's still under development and has limitations regarding tool naming and concurrent calls.

This repository provides a TypeScript-based Model Context Protocol (MCP) client that integrates with LangChain ReAct Agent, enabling interaction with LLMs like Anthropic, OpenAI, and Groq through MCP servers.

This repository provides a Python-based Model Context Protocol (MCP) client using LangChain, enabling interaction with MCP servers through LangChain ReAct Agent and supporting LLMs from Anthropic, OpenAI, and Groq.

This repository showcases a simple Model Context Protocol (MCP) client using LangChain and TypeScript, demonstrating how to convert MCP server tools into LangChain-compatible tools for use with LLMs like Anthropic's Claude.

Trebuchet Tk is a TCL/Tk 8 MUD client designed to provide a user-friendly interface for connecting to and interacting with MUDs, MUCKs, and MUSHes, offering features like color highlighting and script triggering.