https://github.com/datalayer/langchain-mcp-client

🦜🔗 LangChain Model Context Protocol (MCP) Client
https://github.com/datalayer/langchain-mcp-client

langchain mcp-client

Last synced: 9 months ago
JSON representation

🦜🔗 LangChain Model Context Protocol (MCP) Client

• Host: GitHub
• URL: https://github.com/datalayer/langchain-mcp-client
• Owner: datalayer
• License: other
• Created: 2025-02-12T06:44:53.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2025-02-14T10:41:08.000Z (9 months ago)
• Last Synced: 2025-02-14T10:56:10.765Z (9 months ago)
• Topics: langchain, mcp-client
• Language: Python
• Homepage: https://datalayer.tech
• Size: 68.4 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-mcp-servers - **langchain-mcp-client** - 🦜🔗 LangChain Model Context Protocol (MCP) Client `jupyter notebook` `langchain` `mcp` `mcp-client` `mcp-server` `git clone https://github.com/datalayer/langchain-mcp-client` (🤖 AI/ML)
• awesome-mcp-servers - **langchain-mcp-client** - 🦜🔗 LangChain Model Context Protocol (MCP) Client `jupyter notebook` `langchain` `mcp` `mcp-client` `mcp-server` `git clone https://github.com/datalayer/langchain-mcp-client` (AI/ML)

README

          


[![Datalayer](https://assets.datalayer.tech/datalayer-25.svg)](https://datalayer.io)

[![Become a Sponsor](https://img.shields.io/static/v1?label=Become%20a%20Sponsor&message=%E2%9D%A4&logo=GitHub&style=flat&color=1ABC9C)](https://github.com/sponsors/datalayer)

# 🦜 🔗 LangChain MCP Client

[![Github Actions Status](https://github.com/datalayer/langchain-mcp-client/workflows/Build/badge.svg)](https://github.com/datalayer/langchain-mcp-client/actions/workflows/build.yml)

[![PyPI - Version](https://img.shields.io/pypi/v/langchain-mcp-client)](https://pypi.org/project/langchain-mcp-client)

This simple [Model Context Protocol (MCP)](https://modelcontextprotocol.io/)

client demonstrates the use of MCP server tools by LangChain ReAct Agent.

- 🌐 Seamlessly connect to any MCP servers.

- 🤖 Use any LangChain-compatible LLM for flexible model selection.

- 💬 Interact via CLI, enabling dynamic conversations.

## Conversion to LangChain Tools

It leverages a utility function `convert_mcp_to_langchain_tools()` from

[`langchain_mcp_tools`](https://pypi.org/project/langchain-mcp-tools/).  

This function handles parallel initialization of specified multiple MCP servers

and converts their available tools into a list of LangChain-compatible tools

([List[BaseTool]](https://python.langchain.com/api_reference/core/tools/langchain_core.tools.base.BaseTool.html#langchain_core.tools.base.BaseTool)).

## Installation

The python version should be 3.11 or higher.

```bash

pip install langchain_mcp_client

```

## Configuration

Create a `.env` file containing all the necessary `API_KEYS` to access your LLM.

Configure the LLM, MCP servers, and prompt example in the `llm_mcp_config.json5` file:

1. **LLM Configuration**: Set up your LLM parameters.

2. **MCP Servers**: Specify the MCP servers to connect to.

3. **Example Queries**: Define example queries that invoke MCP server tools. Press Enter to use these example queries when prompted.

## Usage

```bash

langchain-mcp-client

```

Below an example with [jupyter-mcp-server](https://github.com/datalayer/jupyter-mcp-server):

![](https://assets.datalayer.tech/jupyter-mcp/jupyter-mcp-server-cli.gif)

## Credits

This initial code of this repo is taken from  from [hideya/mcp-client-langchain-py](https://github.com/hideya/mcp-client-langchain-py) (MIT License).