Simple MCP Client with LangGraph Agent
@simozampa
关于 Simple MCP Client with LangGraph Agent
Simple Multi-Server MCP Client with LangChain
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Simple MCP Client with LangGraph Agent?
A lightweight implementation of a multiserver MCP (Model Context Protocol) client that uses a LangGraph agent for conversations, built with Express.js and TypeScript.
How to use Simple MCP Client with LangGraph Agent?
Clone the repository, install dependencies with npm install, create a .env file with PORT, NODE_ENV, CORS_ORIGIN, and ANTHROPIC_API_KEY, then build and start using npm run build followed by npm start. Use the /api/chat POST endpoint to send messages and configure MCP servers.
Key features of Simple MCP Client with LangGraph Agent
- Express.js server with TypeScript
- LangGraph agent for handling conversations
- MCP client for tool integration
- Streaming responses
Use cases of Simple MCP Client with LangGraph Agent
- Build a chatbot that can call external MCP tools (e.g., weather services)
- Create an agent that orchestrates multiple MCP servers in a single conversation
- Prototype and test MCP integrations with a streaming LangGraph agent
FAQ from Simple MCP Client with LangGraph Agent
What runtime dependencies does it require?
It requires Node.js, Express.js, TypeScript, the Anthropic SDK (for the LangGraph agent), and MCP client libraries. An Anthropic API key must be set in the .env file.
How does authentication work?
The server uses an optional API key per MCP server, passed in the mcpServers array. No other authentication is enforced; CORS can be configured via the CORS_ORIGIN environment variable.
Where is conversation data stored?
Conversation history is passed in the request body (chatHistory) and managed client-side. The server does not persist any data.
What transport does the API use?
The server exposes standard HTTP endpoints (GET and POST). Streaming responses are supported via the ReadableStream API.
Can I use multiple MCP servers in one request?
Yes, the mcpServers array accepts multiple server objects, each with a name, version, and URL. The LangGraph agent will retrieve tools from all specified servers.
AI 与智能体 分类下的更多 MCP 服务器
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Web Agent Protocol
OTA-Tech-AI🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
MCP Claude Code
SDGLBLMCP implementation of Claude Code capabilities and more
21st.dev Magic AI Agent
21st-devIt's like v0 but in your Cursor/WindSurf/Cline. 21st dev Magic MCP server for working with your frontend like Magic
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
评论