home / mcp / persona data mcp server

Persona Data MCP Server

MCP Server generated by mcp.ag2.ai

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "ag2-mcp-servers-personnel-data": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{...}",
        "SECURITY": "YOUR_SECURITY_PARAMS",
        "CONFIG_PATH": "/path/to/mcp_config.json"
      }
    }
  }
}

You run an MCP Server that exposes a modeled context for a given OpenAPI specification. This server lets MCP clients connect in standard, interactive workflows, enabling you to host a local implementation that can be queried and interacted with by MCP clients in your environment.

How to use

Start the MCP server in stdio mode to enable direct control from your local terminal. You will run a Python script that serves the MCP interface, allowing clients to connect, exchange context, and perform operations defined by the server’s configuration.

How to install

Prerequisites you need on your machine before installing and running the server are Python 3.9 or newer, and the pip and uv tooling.

# Step 1: Install dependencies
pip install -e ".[dev]"

# If you prefer to use uv directly for editable installs
uv pip install --editable ".[dev]"

Step-by-step setup to run locally, using the standard development workflow.

# Step 2: Run the MCP server in stdio mode
python mcp_server/main.py stdio

Environment variables you can set to configure the server load at startup. These are optional but can influence behavior in different environments.

CONFIG_PATH=/path/to/mcp_config.json
CONFIG={"mcp": {"name": "persona_data_mcp"}}
SECURITY=your_security_params

Available tools

linting

Use ruff to check code quality and formatting across the project.

formatting

Use ruff format to automatically format code according to style guidelines.

static-analysis

Run static analysis tools (mypy, bandit, semgrep) to catch type issues and security concerns.

testing

Execute tests with pytest and generate coverage reports to verify functionality.

pre-commit

Install and run pre-commit hooks to ensure quality before commits.