MCP Clients

Universal MCP server for AI agents to interact with any* blockchain via natural language and plugins. Supports swaps, bridges, gas, staking, lending, and more across Ethereum, Arbitrum, Base, Polygon, BSC, and testnets.

Self-hosted AI technical workbench. Visual, persistent, multi-stream. Development, architecture, and operational analytics without losing context.

MCPSwiftWrapper is a lightweight wrapper for mcp-swift-sdk, designed to integrate with LLM Swift libraries like SwiftOpenAI and SwiftAnthropic. It simplifies the creation of MCP Clients within macOS applications.

The mcp-langchain-ts-client repository provides a LangChain.js client for the Model Context Protocol, porting the original Python implementation to JavaScript/TypeScript, enabling the use of MCP tools within LangChain.js applications.

Universal Contract AI Interface (UCAI) 🔗 ABI to MCP | The open standard for connecting AI agents to blockchain. MCP server generator for smart contracts. Claude + Uniswap, Aave, ERC20, NFTs, DeFi. Python CLI, Web3 integration, transaction simulation. Polygon, Arbitrum, Base, Ethereum EVM chains. Claude, GPT, LLM tooling, Solidity, OpenAI.

This repository provides an MCP server that integrates Ollama with Claude Desktop, enabling users to list models, get model information, and ask questions to specified models using the Model Context Protocol.

This repository provides a TypeScript implementation of a Model Context Protocol (MCP) client, enabling LLM agents to interact with MCP servers through stdio or HTTP+SSE transports, supporting resources, tools, prompts, and sampling.

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.

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

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

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.

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

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.