Simple MCP Client to Explore MCP Servers

Quickly test and explore MCP servers from the command line!

Project Status

This utility is based on langchain-mcp-tools, which currently supports MCP Protocol version 2025-03-26.

It does not support the MCP 2026-07-28 specification.

Introduction

A simple, text-based CLI client for Model Context Protocol (MCP) servers built with LangChain and Python.
Suitable for testing MCP servers, exploring their capabilities, and prototyping integrations.

Internally it uses LangChain Agent and a utility function convert_mcp_to_langchain_tools() from langchain_mcp_tools.

A TypeScript equivalent of this utility is available here

Prerequisites

• Python 3.11+
• [optional] uv (uvx) installed to run Python package-based local MCP servers
• [optional] npm 7+ (npx) to run Node.js package-based local MCP servers
• LLM API key(s) from OpenAI, Anthropic, Google AI Studio (for GenAI/Gemini), xAI, Cerebras, and/or Groq, as needed

Quick Start

• Install mcp-chat tool. This can take up to a few minutes to complete:

  pip install mcp-chat
  

• Configure LLM and MCP Servers settings via the configuration file, llm_mcp_config.json5

  code llm_mcp_config.json5
  

  The following is a simple configuration for quick testing:

  {
    "llm": {
      "provider": "openai",       "model": "gpt-5.4-mini"
      // "provider": "anthropic",    "model": "claude-haiku-4-5"
      // "provider": "google_genai", "model": "gemini-2.5-flash"
      // "provider": "xai",          "model": "grok-4-1-fast-non-reasoning"
      // "provider": "cerebras",     "model": "gpt-oss-120b"
      // "provider": "groq",         "model": "openai/gpt-oss-20b"
    },
  
    "mcp_servers": {
      "us-weather": {  // US weather only
        "command": "npx", 
        "args": ["-y", "@h1deya/mcp-server-weather"]
      },
    },
  
    "example_queries": [
      "Tell me how LLMs work in a few sentences",
      "Are there any weather alerts in California?",
    ],
  }
  

• Set up API keys

  echo "ANTHROPIC_API_KEY=sk-ant-...
  OPENAI_API_KEY=sk-proj-...
  GOOGLE_API_KEY=AI...
  XAI_API_KEY=xai-...
  CEREBRAS_API_KEY=csk-...
  GROQ_API_KEY=gsk_..." > .env
  
  code .env
  

• Run the tool

  mcp-chat
  

  By default, it reads the configuration file, llm_mcp_config.json5, from the current directory.
  Then, it applies the environment variables specified in the .env file, as well as the ones that are already defined.

Features

• Easy setup: Works out of the box with popular MCP servers
• Flexible configuration: JSON5 config with environment variable support
• Multiple LLM/API providers: OpenAI, Anthropic, Google (GenAI), xAI, Ceberas, Groq
• Command & URL servers: Support for both local and remote MCP servers
• Local MCP Server logging: Save stdio MCP server logs with customizable log directory
• Interactive testing: Example queries for the convenience of repeated testing

Limitations

• Tool Return Types: Currently, only text results of tool calls are supported. It uses LangChain's response_format: 'content' (the default) internally, which only supports text strings. While MCP tools can return multiple content types (text, images, etc.), this library currently filters and uses only text content.
• MCP Features: Only MCP Tools are supported. Other MCP features like Resources, Prompts, and Sampling are not implemented.

Usage

Basic Usage

mcp-chat

By default, it reads the configuration file, llm_mcp_config.json5, from the current directory.
Then, it applies the environment variables specified in the .env file, as well as the ones that are already defined.
It outputs local MCP server logs to the current directory.

With Options

# Specify the config file to use
mcp-chat --config my-config.json5

# Store local (stdio) MCP server logs in specific directory
mcp-chat --log-dir ./logs

# Enable verbose logging
mcp-chat --verbose

# Show help
mcp-chat --help

Supported Model/API Providers

• OpenAI: gpt-5.4-mini, gpt-5.2, etc.
• Anthropic: claude-sonnet-4-6, claude-haiku-4-5, etc.
• Google (GenAI): gemini-3.1-flash-lite-preview, gemini-2.5-flash, etc.
• xAI: grok-4-1-fast-non-reasoning, grok-3-mini, etc.
• Cerebras: gpt-oss-120b, etc.
• Groq: openai/gpt-oss-20b, openai/gpt-oss-120b, etc.

Configuration

Create a llm_mcp_config.json5 file:

• 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

{
  "llm": {
    "provider": "openai",       "model": "gpt-5.4-mini"
    // "provider": "anthropic",    "model": "claude-haiku-4-5"
    // "provider": "google_genai", "model": "gemini-2.5-flash"
    // "provider": "xai",          "model": "grok-4-1-fast-non-reasoning"
    // "provider": "cerebras",     "model": "gpt-oss-120b"
    // "provider": "groq",         "model": "openai/gpt-oss-20b"
  },

  "example_queries": [
    "Read and briefly summarize the llm_mcp_config.json5 file in the current directory",
    "Fetch the raw HTML content from bbc.com and tell me the titile",
    // "Search for 'news in California' and show the first hit",
    // "Tell me about my authenticated GitHub profile",
    // "Tell me about my authenticated Notion account",
  ],

  "mcp_servers": {
    // Local MCP server that uses `npx`
    // https://www.npmjs.com/package/@modelcontextprotocol/server-filesystem
    "filesystem": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-filesystem",
        "."  // path to a directory to allow access to
      ]
    },

    // Local MCP server that uses `uvx`
    // https://pypi.org/project/mcp-server-fetch/
    "fetch": {
      "command": "uvx",
      "args": [
        "mcp-server-fetch"
      ]
    },

    // Embedding the value of an environment variable
    // https://www.npmjs.com/package/@modelcontextprotocol/server-brave-search
    "brave-search": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-brave-search"
      ],
      "env": {
        "BRAVE_API_KEY": "${BRAVE_API_KEY}"
      }
    },

    // Example of remote MCP server authentication via Authorization header
    // https://github.com/github/github-mcp-server?tab=readme-ov-file#remote-github-mcp-server
    "github": {
      // To avoid auto protocol fallback, specify the protocol explicitly when using authentication
      "type": "http",
      "url": "https://api.githubcopilot.com/mcp/",
      "headers": {
        "Authorization": "Bearer ${GITHUB_PERSONAL_ACCESS_TOKEN}"
      }
    },

    // For remote MCP servers that require OAuth, consider using "mcp-remote"
    "notion": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.notion.com/mcp"],
    },
  }
}

Environment Variables

Create a .env file for API keys:

OPENAI_API_KEY=sk-ant-...
ANTHROPIC_API_KEY=sk-proj-...
GOOGLE_API_KEY=AI...
XAI_API_KEY=xai-...
CEREBRAS_API_KEY=csk-...
GROQ_API_KEY=gsk_...

# Other services as needed
GITHUB_PERSONAL_ACCESS_TOKEN=github_pat_...
BRAVE_API_KEY=BSA...

Popular MCP Servers to Try

There are quite a few useful MCP servers already available:

• MCP Server Listing on the Official Site

Troubleshooting

• Make sure your configuration and .env files are correct, especially the spelling of the API keys
• Check the local MCP server logs
• Use --verbose flag to view the detailed logs
• Refer to Debugging Section in MCP documentation

Building from Source

See README_DEV.md for details.

Change Log

Can be found here

License

MIT License - see LICENSE file for details.

Contributing

Issues and pull requests welcome!
In particular, please share any issues relating to the latest versions of LLM models and specific MCP servers.
This tool aims to make MCP server testing as simple as possible.