MCP Client Langchain Py

2 forks

4 stars

Free

What is mcp-client-langchain-py

mcp-client-langchain-py is a user-friendly client designed to demonstrate the integration of Model Context Protocol (MCP) server tools using the LangChain ReAct Agent. Developed by Hideya, this client facilitates the seamless interaction between AI models and various data sources through MCP, a protocol that allows AI systems to securely connect with external tools and information. The client leverages the utility function convert_mcp_to_langchain_tools() to convert MCP server tools into LangChain-compatible tools, supporting AI models from Anthropic, OpenAI, and Groq.

How to Use mcp-client-langchain-py

To get started with mcp-client-langchain-py, ensure you have Python 3.11 or higher and, optionally, uv or npm if you plan to run MCP servers through Python or Node.js packages, respectively. You'll also need API keys from Anthropic, OpenAI, or Groq.

Setup Steps:

Install Dependencies: Open your terminal and run:
```
make install
```
Configure API Keys: Copy the template file and update it with your API keys:
```
cp .env.template .env
```
Ensure your .env file contains all necessary credentials, protected from accidental commits by .gitignore.
Adjust Configuration: Modify the llm_mcp_config.json5 file to set up your LLM and MCP server settings. This JSON5 format allows comments and trailing commas, and supports environment variable interpolation with ${...} notation.

Running the Client:

Start the application:
```
make start
```
Note that the initial run may take some time.
To run in verbose mode:
```
make start-v
```
For help with command-line options:
```
make start-h
```

Once running, you can press Enter at the prompt to use example queries for MCP server tool invocations. These example queries can be customized within the llm_mcp_config.json5 file.

Key Features of mcp-client-langchain-py

Seamless Integration with MCP: Utilizes the Model Context Protocol to connect AI systems with external data sources securely and efficiently.
LangChain Compatibility: Converts MCP server tools into LangChain-compatible tools, enabling robust AI interactions.
Support for Multiple LLMs: Works with language models from Anthropic, OpenAI, and Groq, offering flexibility and choice.
Customizable Configuration: Offers a flexible configuration setup using JSON5, allowing comments and environment variable references for secure and adaptable setups.
Ease of Use: Simple setup and operation with command-line interface options for starting, running in verbose mode, and configuring queries.

This client is ideal for users looking to bridge AI models with diverse data sources, leveraging the power of MCP with the flexibility of LangChain tools.

This simple Model Context Protocol (MCP) client demonstrates the use of MCP server tools by LangChain ReAct Agent. It leverages a utility function convert_mcp_to_langchain_tools() from 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]). LLMs from Anthropic, OpenAI and Groq are currently supported. A typescript version of this MCP client is available here

Prerequisites

Python 3.11+
optional] [uv (uvx) installed to run Python package-based MCP servers
optional] [npm 7+ (npx) to run Node.js package-based MCP servers
API keys from Anthropic, OpenAI, and/or Groq as needed

Setup

Install dependencies:

make install

Setup API keys:

cp .env.template .env

Update .env as needed.
.gitignore is configured to ignore .env to prevent accidental commits of the credentials.

Configure LLM and MCP Servers settings llm_mcp_config.json5 as needed.

The configuration file format for MCP servers follows the same structure as Claude for Desktop, with one difference: the key name mcpServers has been changed to mcp_servers to follow the snake_case convention commonly used in JSON configuration files.
The file format is JSON5, where comments and trailing commas are allowed.
The format is further extended to replace ${...} notations with the values of corresponding environment variables.
Keep all the credentials and private info in the .env file and refer to them with ${...} notation as needed.

Usage

Run the app:

make start

It takes a while on the first run. Run in verbose mode:

make start-v

See commandline options:

make start-h

At the prompt, you can simply press Enter to use example queries that perform MCP server tool invocations. Example queries can be configured in llm_mcp_config.json5

How to Use

To use the mcp-client-langchain-py, follow these steps:

Visit https://github.com/hideya/mcp-client-langchain-pyhttps://github.com/hideya...
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using mcp-client-langchain-py capabilities within your Claude conversations