ATWork

MCP Server generated by mcp.ag2.ai

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": {
    "rashed-mamoon-atwork-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"transport\":\"stdio\"}",
        "SECURITY": "{\"apiKey\": \"YOUR_API_KEY\"}",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

You can run an MCP server that exposes the OpenAPI-based endpoints for client interactions. This server lets you communicate with a defined API surface using the Multi-Agent Conversation Protocol, enabling structured agent collaboration and flexible transport modes. It is designed to be easy to run locally for development and testing, with simple environment-based configuration.

How to use

You connect to the MCP server from an MCP client and start conversations with agents through the protocol’s transport modes. In practice, you will choose a transport mode that fits your environment (stdio for local development, or other modes if provided) and then initiate interactions via the client using the API surface defined by the OpenAPI specification. Use the configured security parameters to authenticate requests when required, and provide a configuration file or environment variables as needed to tailor the server behavior to your setup.

How to install

Prerequisites you need before installing the MCP server are Python 3.9 or newer, and the Python package manager tools pip and uv.

Step 1: Prepare your environment

Step 2: Install dependencies

# Method A: install in a development environment
pip install -e ".[dev]"

# Method B: install via uv (alternative)
uv pip install --editable ".[dev]"

Run the MCP server

Start the MCP server in stdio mode using the built-in entry point.

python mcp_server/main.py stdio

Configuration and security

Configure the server using environment variables. You can provide a JSON configuration via a file path or a JSON string. Security-related settings are supplied through environment variables to protect access to the MCP endpoints.

Environment variables you may use include:

# Examples (placeholders show intent)
export CONFIG_PATH=mcp_server/mcp_config.json
export CONFIG='{"transport":"stdio"}'
export SECURITY='{"apiKey": "YOUR_API_KEY"}'

Tests and quality checks

The project uses linting, static type checking, and tests to ensure quality. Run the following to check linting and formatting, or execute the provided scripts for convenience.

ruff check
ruff format
./scripts/static-analysis.sh
./scripts/test.sh