Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
langchain-mcp-adapters
LangChain 🔌 MCP
3.6kstars
442forks
Python
langchainlanggraphmcppythontools
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Turns MCP-compatible tools into LangChain tools so LangGraph agents can use them.
Use this when
- Need to use MCP tools in a LangGraph agent
- Want to connect multiple MCP servers to one agent
- Building agents that call external APIs via MCP
- Testing MCP tools locally before production use
- Adding custom tools to an existing LangChain workflow
Don't use when
- If you only need MCP tools in a non-LangChain context
- When your MCP tools are already natively supported by your LLM
- If you're not using LangGraph or LangChain agents
Capabilities
- Converts MCP tools into LangChain tools
- Supports multiple MCP servers in one agent
- Works with stdio, HTTP, and streamable HTTP MCP transports
- Allows passing runtime headers for MCP server auth
- Integrates with LangGraph StateGraph for agent workflows
- Provides async/await support for MCP tool loading
InstallMCPRun via uvx (Python)
Universal installANY TOOL
$ npx skillcity@latest langchain-ai/langchain-mcp-adaptersAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
uvx langchain-mcp-adapters
MCP Configuration
Add this to your claude_desktop_config.json
{
"mcpServers": {
"langchain-mcp-adapters": {
"command": "uvx",
"args": [
"langchain-mcp-adapters"
]
}
}
}Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
langchain-mcp-adapters — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt