The IMDB Data Access MCP Server is a Model Context Protocol (MCP) server designed to provide access to IMDB data. It implements a simple note storage system with custom URI schemes and tools for managing and summarizing notes.
The server implements a simple note storage system with:
- Custom note://
URI scheme for accessing individual notes.
- Each note resource has a name
, description
, and text/plain
mimetype.
The server provides a single prompt:
- summarize-notes
: Creates summaries of all stored notes.
- Optional style
argument to control detail level (brief
/detailed
).
- Generates a prompt combining all current notes with style preference.
The server implements one tool:
- add-note
: Adds a new note to the server.
- Takes name
and content
as required string arguments.
- Updates server state and notifies clients of resource changes.
[TODO: Add configuration details specific to your implementation]
~/Library/Application\ Support/Claude/claude_desktop_config.json
%APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"mcp-imdb": {
"command": "uv",
"args": [
"--directory",
"/git/mcp-imdb",
"run",
"mcp-imdb"
]
}
}
"mcpServers": {
"mcp-imdb": {
"command": "uvx",
"args": [
"mcp-imdb"
]
}
}
To prepare the package for distribution:
1. Sync dependencies and update lockfile:
shell
uv sync
2. Build package distributions:
shell
uv build
3. Publish to PyPI:
shell
uv publish
Note: Set PyPI credentials via environment variables or command flags:
- Token: --token
or UV_PUBLISH_TOKEN
- Or username/password: --username
/UV_PUBLISH_USERNAME
and --password
/UV_PUBLISH_PASSWORD
For the best debugging experience, use the MCP Inspector. Launch it with:
npx @modelcontextprotocol/inspector uv --directory <dir_to>/git/mcp-imdb run mcp-imdb
The IMDB Data Access MCP Server is licensed under the MIT License.