Parts Mcp

Please install the `parts-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Python 3.10+** — Python 3.10 or newer is required to run the server.
- **Install uv** — The recommended launch method uses uvx, which requires uv to be installed. (https://docs.astral.sh/uv/)
- **Obtain a Source Parts API key** — Required for the local stdio server configuration. (https://source.parts/docs/api)

Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["parts-mcp"]
- required environment variables:
  - `SOURCE_PARTS_API_KEY`: Source Parts API key used to authenticate requests to the Source Parts API. (example: `<your-api-key>`)
- optional environment variables:
  - `SOURCE_PARTS_API_URL`: Override for the Source Parts API base URL. (example: `<your-api-url>`)
  - `KICAD_SEARCH_PATHS`: Path or paths to search for local KiCad projects. (example: `<your-kicad-project-paths>`)
  - `PARTS_CACHE_DIR`: Directory for local cache storage. (example: `<your-cache-directory>`)
  - `CACHE_EXPIRY_HOURS`: Cache expiration time in hours. (example: `<cache-expiry-hours>`)

Note: README also documents a hosted remote connector for claude.ai at https://mcp.source.parts/ using OAuth and no API key, but it does not provide a canonical MCP HTTP/SSE config shape beyond the connector URL. Preferred portable local configuration is the stdio uvx launch.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.