# LangChain Docs MCP server

> Search and read the LangChain, LangGraph and LangSmith documentation, with code examples and API references, from your assistant.

- Listing: https://mcp.tc/i/langchain-docs
- Connect: use the server's own URL `https://docs.langchain.com/mcp` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint.
- Type: remote (Streamable HTTP)
- Auth: none
- Category: [Docs & Knowledge](https://mcp.tc/c/docs-knowledge)
- Vendor: LangChain
- Homepage: <https://docs.langchain.com/oss/python/langchain/mcp>

## About

Connects an assistant to the Docs by LangChain site. It can search guides, how-tos, code examples and API references, and read full pages through a virtual, read-only filesystem of the documentation and OpenAPI specs. A feedback tool lets it report incorrect or outdated pages to the docs team.

The server is a hosted streamable HTTP endpoint at https://docs.langchain.com/mcp. It is public, so no sign-in or API key is needed. Apart from submitting feedback, it is read-only and limited to the published documentation.

## What it can do

- Search LangChain docs for guides, examples and API references
- Read full documentation pages by path with head or cat
- Search docs with exact keyword or regex matches
- Report incorrect or outdated pages to the docs team

## Tools (3)

- `search_docs_by_lang_chain`: Search the LangChain docs for guides, how-tos, code examples and API references. (read-only)
- `query_docs_filesystem_docs_by_lang_chain`: Run read-only shell-like commands (rg, head, cat) over a virtual filesystem of the docs. (read-only)
- `submit_feedback`: Report an incorrect, outdated or incomplete documentation page to the docs team.

## Example prompts

- "How do I add short-term memory to a LangChain agent?"
- "Find the LangGraph docs on human-in-the-loop interrupts."
- "Show me the docs page about LangSmith observability setup."
- "Search the LangChain docs for how MCPAdapter handles authentication."

## Install

### Claude Code

1. Run this in a terminal, in your project folder:

```bash
claude mcp add --transport http langchain-docs https://docs.langchain.com/mcp
```

2. Start Claude Code and type `/mcp`. **langchain-docs** should show as connected.

Add `--scope user` to make it available in every project, not just this one.

### Claude Desktop

1. Open **Settings → Connectors** and click **Add custom connector**.

2. Name it **LangChain Docs** and paste this URL:

```url
https://docs.langchain.com/mcp
```

3. Click **Add**. Its tools appear in the chat’s tools menu.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

### claude.ai

1. Open the connector form on claude.ai. This button fills in the name and URL for you:

[Add to claude.ai](<https://claude.ai/customize/connectors?modal=add-custom-connector&connectorName=LangChain%20Docs&connectorUrl=https%3A%2F%2Fdocs.langchain.com%2Fmcp>) (opens connector settings)

2. Check that the URL reads `https://docs.langchain.com/mcp` and click **Add**.

3. Turn it on in a chat from the tools menu.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**.

### ChatGPT

1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**.

2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server.

3. Paste `https://docs.langchain.com/mcp` as the server URL and choose **No authentication**.

Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts.

### Cursor

[Add to Cursor](<https://cursor.com/install-mcp?name=langchain-docs&config=eyJ1cmwiOiJodHRwczovL2RvY3MubGFuZ2NoYWluLmNvbS9tY3AifQ%3D%3D>) (opens Cursor)

Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project):

`mcp.json`:

```json
{
  "mcpServers": {
    "langchain-docs": {
      "url": "https://docs.langchain.com/mcp"
    }
  }
}
```

### VS Code

[Install in VS Code](<https://vscode.dev/redirect/mcp/install?name=langchain-docs&config=%7B%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fdocs.langchain.com%2Fmcp%22%7D>) (opens VS Code)

Or from a terminal:

```bash
code --add-mcp '{"name":"langchain-docs","type":"http","url":"https://docs.langchain.com/mcp"}'
```

Or commit it to the repo in `.vscode/mcp.json`:

`.vscode/mcp.json`:

```json
{
  "servers": {
    "langchain-docs": {
      "type": "http",
      "url": "https://docs.langchain.com/mcp"
    }
  }
}
```

### Devin Desktop

1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows):

`mcp_config.json`:

```json
{
  "mcpServers": {
    "langchain-docs": {
      "serverUrl": "https://docs.langchain.com/mcp"
    }
  }
}
```

2. Refresh the MCP server list in Cascade.

Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers.

### Codex

```bash
codex mcp add langchain-docs --url https://docs.langchain.com/mcp
```

Or edit `~/.codex/config.toml` directly:

`config.toml`:

```toml
[mcp_servers.langchain-docs]
url = "https://docs.langchain.com/mcp"
```

### Gemini CLI

```bash
gemini mcp add --transport http langchain-docs https://docs.langchain.com/mcp
```

This adds it to the current project. Add `-s user` to use it everywhere.

### Any client

Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file.

```json
{
  "mcpServers": {
    "langchain-docs": {
      "type": "http",
      "url": "https://docs.langchain.com/mcp"
    }
  }
}
```

Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE.

Client only starts local servers? Bridge it with `npx -y mcp-remote https://docs.langchain.com/mcp`.

## Details

- Server version: 1.0.0
- MCP protocol version: 2026-07-28
- Last checked: 2026-10-03 (reachable)
- Listed: 2026-10-03
- Updated: 2026-10-04

---
Source: https://mcp.tc/i/langchain-docs (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report
