stash_mcp_server

This MCP server provides a focused toolkit for querying and analyzing a Stash instance. It exposes a concise set of prompts and tools to fetch performer data, generate insights, and surface personalized scene recommendations. You can use commands to get performer information, list all performers with advanced filters, retrieve scenes for a performer, and run strategic insights like library analytics or health checks. The server is designed to be composable, so you can chain tools or call individual endpoints to build your own analysis workflows against your Stash installation.

Prerequisites:

• Python 3.9+ installed on your system
• Git installed
• Access to a Stash instance (self-hosted or cloud) with appropriate API credentials if required

Installation steps:

1. Clone the repository git clone https://github.com/donlothario/stash_mcp_server.git cd stash_mcp_server

2. (Optional but recommended) Create and activate a virtual environment python -m venv venv source venv/bin/activate # On Windows use: venv\Scripts\activate.bat

3. Install dependencies pip install -U pip if an installation file exists, install from source: pip install -e . or install requirements if provided: pip install -r requirements.txt

4. Run the MCP server python -m stash_mcp_server

5. Configure mcp_config for your environment as shown in the example above, adjusting STASH_API_URL and credentials as needed.

Notes and tips:

• Ensure your Stash API URL is reachable from the MCP server host and that any required authentication tokens are configured via environment variables.
• The server includes prompts such as analyze-performer, library-insights, and recommend-scenes, plus a suite of tools for performer and scene data. You can adjust caching and log levels via environment variables.
• If running behind a firewall or in a container, expose necessary ports and set appropriate network policies.
• For production deployments, consider mounting a persistent cache directory and enabling structured logging.