# LangChain Integration

> Use this tool when you need to integrate Model Context Protocol (MCP) tools into LangChain workflows, enabling AI assistants to leverage external services and data sources. It solves problems of compatibility and complexity by abstracting away MCP communication and presenting tools as standard LangChain BaseTools. This integration is ideal for LangChain developers looking to expand their AI applications' capabilities with MCP-compatible tools, providing a seamless interface for incorporating new functionalities into existing codebases.

Canonical page: https://skillsregistry.net/skills/rectalogic-langchain  
JSON: https://api.skillsregistry.net/v1/skills/rectalogic-langchain

## Description

This LangChain integration, developed by rectalogic, enables AI assistants (powered by LangChain) to leverage Model Context Protocol (MCP) tools within the LangChain framework. It provides an MCPToolkit class that wraps an MCP ClientSession, allowing seamless incorporation of MCP capabilities into LangChain workflows. Built in Python, the implementation abstracts away the complexities of MCP communication, presenting tools as standard LangChain BaseTools. By bridging LangChain's flexible architecture with MCP's extensible toolset, this integration enhances AI models' ability to interact with external services and data sources. It is particularly useful for developers already using LangChain who want to expand their AI applications' capabilities with MCP-compatible tools without significant changes to their existing codebase.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rectalogic-langchain)
- **Repository:** <https://github.com/rectalogic/langchain-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "rectalogic-langchain"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rectalogic-langchain` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rectalogic-langchain/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt