Pokapi

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": {
    "kumaranvpl-pokapi": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{...} (JSON string) ",
        "SECURITY": "API_KEYS or other security parameters",
        "CONFIG_PATH": "path/to/mcp_config.json"
      }
    }
  }
}

You run a dedicated MCP server that enables multi-agent conversations against a defined API surface. This server scaffolds how agents communicate, coordinate, and share context, making it easier to build interactive AI workflows that rely on a consistent protocol.

How to use

You connect an MCP client to the server to start multi-agent conversations. Start the server in stdio mode and use a client to send requests that follow the MCP protocol. The server exposes a straightforward runtime that accepts a startup command and a mode, then processes agent messages, routing them to the appropriate handlers. Configure your client to point at the server’s runtime, and use the provided environment variables to control security and configuration.

How to install

Prerequisites: You need Python 3.9 or newer, and you should have pip and uv available.

Step 1: Clone the project and navigate to the MCP server directory.

git clone <repository-url>
cd mcp_server

Steps to set up and run the server locally

Step 2: Install dependencies in editable dev mode.

pip install -e ".[dev]"

Alternative: run with uv if you prefer a different runtime

Step 3: Use uv to install in editable mode as an alternative.

uv pip install --editable ".[dev]"

Run the MCP server

Step 4: Start the server in stdio mode using the standard Python invocation.

python mcp_server/main.py stdio

Configuration and environment variables

You can influence runtime behavior using environment variables.

CONFIG_PATH: Path to a JSON configuration file (for example, mcp_server/mcp_config.json).
CONFIG: A JSON string containing the configuration.
SECURITY: Environment variables for security parameters (such as API keys).

Starting details and notes

Explicit startup usage is shown in the standard command above. The server’s main entry checks how to load configuration and applies security settings as defined by the environment. When you run the server in stdio mode, you interact with it through the process I/O channels as your MCP client sends requests and receives responses.

Development and quality tooling

The project uses several quality and testing tools to maintain code health. You can run them locally to ensure code quality before commits.

ruff check
ruff format
./scripts/static-analysis.sh
./scripts/test.sh
pre-commit install

Building and publishing

Build and publish steps are available through the project’s build tooling.

hatch build
hatch publish

Notes on security and configuration

Keep security parameters in the SECURITY environment variable set and provide a JSON configuration via CONFIG or a configuration file path via CONFIG_PATH to control access and behavior.

Troubleshooting tips

If the server does not start, verify that Python 3.9+ is installed, required dependencies are present, and you are running the command in the correct directory where mcp_server/main.py resides.

Available tools

ruff

Lints and formats the codebase to ensure consistent style and catch potential issues.

mypy

Performs static type checking to catch type errors before runtime.

pytest

Runs test suites to verify functionality and regressions.

pre-commit

Runs a set of checks before each commit to maintain code quality.