MCP Clients

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

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

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 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 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 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.

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 provides a LangChain client for the Model Context Protocol, enabling seamless connection to MCP servers. It converts MCP tools for use with LangChain, facilitating dynamic conversations.

Agsync is a repo-native control plane for managing skills, MCP servers, secrets, and agent configs across AI clients like Claude Code and Cursor.

MCP server + Ollama-driven autonomous penetration testing client. Connects LLMs to security tools (nmap, nikto, sqlmap, dalfox…) via Model Context Protocol with session management, output parsing, and findings persistence.

This repository provides an example client implementation using the Vercel AI SDK and Model Context Protocol SDK to streamline LLM chat interactions within a browser environment, including tool discovery and usage.

VULCA — AI-native cultural art creation & evaluation SDK. L1-L5 scoring, layer editing, self-evolution. 1104 tests, 21 MCP tools, 13 traditions.

Litemcp simplifies SDK adoption into MCP by providing a lightweight client for integrating AI SDKs like LangChain and Agent SDK, emphasizing simplicity, flexibility, and minimal dependencies. Litemcp simplifies SDK adoption

KSeF SDK for TypeScript/Node.js — invoice reconciliation with bank statements (MT940, mBank, ING, PKO, Santander), production KSeF 2.0 HTTP client, MCP server for Claude and Cursor. Open-source, MIT.