mcpField
M
MCP Client

MCP Client

github.com/swairshahFrameworks & SDKs1Updated 87w ago
Repository

About MCP Client

MCP Client is a basic Model Context Protocol client that reads server configuration from servers_config.json and communicates with MCP-compatible servers. Includes example servers in Node.js and Python.

Key features

  1. 01MCP protocol client implementation
  2. 02Configuration file support
  3. 03Command-line interface
  4. 04Multi-server connectivity

Use cases

  1. 01Connect to and test MCP servers
  2. 02Integrate third-party MCP server implementations
  3. 03Prototype MCP-based applications

MCP support

MCP Client is an MCP client that manages and connects to multiple MCP servers via servers_config.json configuration, supporting both official and custom-built servers.

Details

From the project README

MCP Client

A basic Model Context Protocol (MCP) client implementation with example servers - one in Node.js and one in Python.

Overview

This repository contains a simple implementation of an MCP client that can communicate with MCP-compatible servers.

Setup

  1. Install Python dependencies:

    pip install -r requirements.txt

  2. Configure servers in servers_config.json e.g.

{
  "mcpServers": {
    "git": {
      "command": "uvx",
      "args": ["mcp-server-git", "--repository", "."]
    },
    "puppeteer": {
      "command": "npx",
      "args": ["-y", "@modelcontextprotocol/server-puppeteer"]
    }
  }
}

You can get the list of available servers [!here][https://github.com/modelcontextprotocol/servers].

Or write your own. For that add config something like:

"zotero-mcp-server": {
        "command": "bash",
        "args": [
          "-c",
          "cd /Users/swair/zotero-mcp-server && source .venv/bin/activate && python -m zotero_mcp.server"
        ]
      },

Running the Client

python client.py

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.