MCP Clients

Laravel MCP is a package that implements the Model Context Protocol, enabling communication between AI models and Laravel applications through standardized interfaces with features like tool registration and resource management.

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.

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

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

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

MCP server for analyzing Perfetto traces with LLMs — query .pftrace files in PerfettoSQL via Claude Code or any MCP client

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

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.

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

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.

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

Curated list of Model Context Protocol (MCP) servers, clients, and frameworks. Automatically updated daily.

Persistent, auditable, contradiction-safe memory for coding agents. Hybrid BM25 + vector retrieval, 19 MCP tools, co-retrieval graph, MIND-accelerated scoring. Zero external dependencies.

Enable AI-driven automated Android dynamic analysis by controlling Frida through the Model Context Protocol for streamlined reverse engineering.