langchain-mcp-adapters and mcp-client-langchain-ts
These are complements: the official LangChain adapter provides the integration layer for LangChain agents to use MCP servers, while the TypeScript implementation builds a concrete ReAct agent CLI on top of that adapter.
About langchain-mcp-adapters
langchain-ai/langchain-mcp-adapters
LangChain 🔌 MCP
This project helps AI developers integrate external capabilities, like custom calculators or data lookups, into their LangChain or LangGraph AI agents. It takes existing 'Model Context Protocol' (MCP) tools, which are essentially specialized functions, and makes them accessible to the AI agent. The result is an AI agent that can perform a wider range of tasks by using these external tools.
About mcp-client-langchain-ts
hideya/mcp-client-langchain-ts
Simple MCP Client CLI Implementation Using LangChain ReAct Agent / TypeScript
This is a command-line tool for developers who work with AI models and want to quickly test and explore Model Context Protocol (MCP) servers. It takes your configuration for MCP servers and LLMs, letting you interact with these servers using text-based commands and receive text-based responses. This is ideal for AI/ML engineers or researchers who are building or integrating with MCP servers.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work