mcp-langchain-ts-client
@isaacwasserman
关于 mcp-langchain-ts-client
LangChain.js client for Model Context Protocol.
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 mcp-langchain-ts-client?
It is a LangChain.js client for the Model Context Protocol (MCP), ported from the Python library rectalogic/langchain-mcp to the JavaScript/TypeScript ecosystem.
How to use mcp-langchain-ts-client?
Install via npm install mcp-langchain-ts-client. Create an MCPToolkit instance with server parameters (command and args), call await toolkit.initialize(), then access toolkit.tools to retrieve LangChain.js‑compatible tools. The tools can be passed directly to LangChain agents, for example using createReactAgent from @langchain/langgraph/prebuilt.
Key features of mcp-langchain-ts-client
- LangChain.js integration for Model Context Protocol tools.
MCPToolkitclass to spawn and manage MCP servers.- Extracts MCP tools as LangChain.js
StructuredToolinstances. - Supports any MCP server runnable via command line.
- Simple initialization and tool retrieval workflow.
Use cases of mcp-langchain-ts-client
- Connect a LangChain agent to MCP‑compatible tools (e.g.,
@modelcontextprotocol/server-everything). - Build LangGraph workflows that leverage MCP server resources.
- Port Python‑based MCP‑LangChain integrations to JavaScript/TypeScript projects.
FAQ from mcp-langchain-ts-client
What is the relationship to rectalogic/langchain-mcp?
This package is a port of the Python library rectalogic/langchain-mcp to the JavaScript/TypeScript LangChain and MCP APIs.
What runtime does it require?
It requires Node.js (implied by npm installation and use of npx to launch MCP servers).
How do I obtain LangChain‑compatible tools from an MCP server?
Create an MCPToolkit instance with the server’s command and arguments, call initialize(), then access the tools property.
Does it work with any MCP server?
It works with any MCP server that can be launched as a subprocess using a command and args (e.g., @modelcontextprotocol/server-everything).
AI 与智能体 分类下的更多 MCP 服务器
mcp-hfspace MCP Server 🤗
evalstateMCP Server to Use HuggingFace spaces, easy configuration and Claude Desktop mode.
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Unreal Engine Generative AI Support Plugin
prajwalshettydevUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agenti
欢迎来到 智言平台
Shy2593666979AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
评论