MCP Client Langchain Ts

0 forks

6 stars

Free

What is mcp-client-langchain-ts

mcp-client-langchain-ts is a client application developed by hideya that utilizes the Model Context Protocol (MCP) to connect AI systems with various data sources and tools. This client serves as a demonstration of how MCP servers can be leveraged by LangChain's ReAct Agent. By converting MCP server tools into LangChain-compatible tools, mcp-client-langchain-ts enables AI models to access and utilize structured data and external tools efficiently. This application supports Language Models (LLMs) from providers such as Anthropic, OpenAI, and Groq, making it versatile for different AI use cases.

How to Use mcp-client-langchain-ts

Prerequisites:

Ensure you have Node.js 16+ and npm 7+ installed on your system.
Obtain API keys from Anthropic, OpenAI, and/or Groq, depending on your use case.

Setup Instructions:

Install Dependencies: Open your terminal and run the following command to install necessary dependencies:
```
npm install
```
Configure API Keys: Copy the .env.template file to .env and update it with your API keys. This ensures secure and private storage of your credentials.
Configure Server Settings: Adjust the llm_mcp_config.json5 file to set up your LLM and MCP server configurations. This file allows for comments and trailing commas, making it user-friendly for edits. Use environment variables for sensitive information referenced in the file.

Running the Application:

To start the application, execute:
```
npm start
```
For verbose output, use:
```
npm run start:v
```
To view available command-line options, enter:
```
npm run start:h
```

At the command prompt, you can use predefined example queries to interact with MCP server tools. These examples can be customized in the llm_mcp_config.json5 file.

Key Features of mcp-client-langchain-ts

MCP Integration: Seamlessly connects AI systems with external data sources and tools through the Model Context Protocol, providing a robust framework for accessing real-time information.
LangChain Compatibility: Converts MCP server tools into LangChain-compatible tools, allowing for a streamlined integration with the LangChain ReAct Agent.
Multi-LLM Support: Compatible with leading language models from Anthropic, OpenAI, and Groq, providing flexibility and choice for different AI applications.
User-Friendly Configuration: Utilizes a JSON5 configuration file, which supports comments and trailing commas, for easy setup and maintenance. Environment variable placeholders ensure that sensitive information remains secure and private.
Extensive Command-Line Options: Offers various command-line options for running the application, including verbose mode for detailed output and help mode for guidance on usage.

This overview provides a comprehensive yet concise guide to understanding and using the mcp-client-langchain-ts application for AI-driven projects. Whether you're a developer or a non-technical user, this tool can enhance your AI system's capabilities by providing secure access to a wide range of data and tools.

This simple Model Context Protocol (MCP) client demonstrates the use of MCP server tools by LangChain ReAct Agent. It leverages a utility function convertMcpToLangchainTools() from @h1deya/langchain-mcp-tools. This function handles parallel initialization of specified multiple MCP servers and converts their available tools into an array of LangChain-compatible tools (StructuredTool). LLMs from Anthropic, OpenAI and Groq are currently supported. A python version of this MCP client is available here

Prerequisites

Node.js 16+
npm 7+ (npx) to run Node.js-based MCP servers
optional] [uv (uvx) installed to run Python-based MCP servers
API keys from Anthropic, OpenAI, and/or Groq as needed.

Setup

Install dependencies:

npm 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:

npm start

Run in verbose mode:

npm run start:v

See commandline options:

npm run 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-ts, follow these steps:

Visit https://github.com/hideya/mcp-client-langchain-tshttps://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-ts capabilities within your Claude conversations