Discovery API

This MCP server exposes a machine-readable API for the Ticketmaster Discovery OpenAPI specification, enabling clients to interact with the discovery data through the MCP protocol. It provides a stable, versioned entry point you can connect to from MCP clients, simplifying integration and testing.

How to use

Connect your MCP client to the Discovery MCP Server using the http endpoint or run the local stdio server. The server presents a consistent MCP interface for querying the Ticketmaster Discovery API, so you can fetch discovery data, schemas, and related endpoints without embedding direct API calls in your client.

How to install

# Prerequisites
- Python 3.9+
- pip
- uv (optional, for running the server via uv)

# Installation from source
# 1) Clone the repository
git clone <repository-url>
cd mcp-server

# 2) Install dependencies (dev dependencies enabled)
pip install -e ".[dev]"

# Alternatively, use uv to install editable dev dependencies
# (if you prefer using uv tooling)
uv pip install --editable ".[dev]"

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

Configuration and runtime notes

Configure and run options are available via environment variables shown below. You can point the server to a configuration file or pass a JSON string directly. Security-related parameters can be supplied via environment variables as well.

# Examples of environment variables you can set
CONFIG_PATH=/path/to/mcp_server/mcp_config.json
CONFIG='{"server": {"name": "ticketmaster_discovery"}}'
SECURITY=API_KEY=YOUR_API_KEY

Notes on running and testing

The server supports multiple transport modes. The most common usage is to run it in stdio mode during development or when embedding the MCP server in tooling. You can also connect via an HTTP-based MCP URL if you expose the server remotely.

Build and publish

# Build and publish using Hatch
hatch build
hatch publish

Available tools

ruff

Linting and formatting tool used to enforce code style and quality.

mypy

Static type checker used to ensure type correctness across the codebase.

pytest

Testing framework used to run unit and integration tests.

pre-commit

Pre-commit hooks configured to run linting, type checks, and tests before commits.

hatch

Build and publish tool used to package the MCP server.