MCP servers · publisher
MCP servers by langchain-ai
langchain-ai publishes 3 MCP servers in the atlas. 2 are SAFE, 0 CAUTION and 1 BLOCK. Each was read in full before it was listed.
Cite
Cite this page
ModelsAtlas. “MCP servers by langchain-ai”. Retrieved 28 Oct 2026. https://modelsatlas.com/mcp/langchain-ai
Verdicts · 3 servers
Transports
- stdio, runs locally2
- Streamable HTTP, remote2
- SSE, legacy remote2
A server can list more than one transport.
Tool risk
1
server expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 7 tools.
Servers with no destructive tools →3 servers by langchain-ai
1–3 of 3 · ranked by trust score, then stars
Mcpdoc
langchain-ai/mcpdoc
Expose llms-txt to IDEs for development
LangChain.js MCP Adapters
langchain-ai/langchainjs-mcp-adapters
** THIS REPO HAS MOVED TO https://github.com/langchain-ai/langchainjs/tree/main/libs/langchain-mcp-adapters ** Adapters for integrating Model Context Protocol (MCP) tools with LangChain.js applications, supporting both stdio and SSE transports.
Langchainjs
langchain-ai/langchainjs
The agent engineering platform
More from langchain-ai
Questions
Which langchain-ai MCP server has the best trust score?
Are langchain-ai's MCP servers read-only?
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Which langchain-ai MCP server has the best trust score?
- Are langchain-ai's MCP servers read-only?