Public

A simple public mcp server

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "pankhur-public-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/Pankhur/public-mcp.git",
        "mcp-server"
      ]
    }
  }
}

You can run a Model Context Protocol (MCP) server to host and serve model context data to MCP clients. This server enables seamless interactions with various clients that rely on MCP for exchanging context and actions in your environment.

How to use

You connect to the MCP server using an MCP client and perform actions such as querying, updating, or subscribing to model context data. Start the server using your preferred runtime, then point your MCP client at the server endpoint. If you use a standard local setup, you’ll typically run the server locally and then direct clients to http://localhost:PORT or the appropriate socket if you are using a stdio-based workflow.

How to install

# Prerequisites
- Python 3.x installed
- pip available
- uvx (for quick setup) or manual installation flow

# 1) Quick setup with uvx (recommended)
{
  "public-mcp": {
    "command": "uvx",
    "args": [
      "--from",
      "git+https://github.com/Pankhur/public-mcp.git",
      "mcp-server"
    ]
  }
}

# 2) Manual installation
# a) Clone the repository
git clone https://github.com/Pankhur/public-mcp.git
cd public-mcp

# b) Install dependencies
pip install -e .

# Alternatively, install dependencies using uv
pip install uv
uv pip install -e .

Additional notes

After installing, you can run the server directly using Python. This starts the MCP server in the current environment and makes it available to MCP clients.