← Index

Project Gutenberg MCP

io.github.bobbyhouse/project-gutenberg-mcp·v1.2.0·Search
Quality Score
95
/100

Read Project Gutenberg books via MCP. Search, fetch metadata, and retrieve text in passages.

§01  Install
Claude Desktop (Docker)
{
  "mcpServers": {
    "project-gutenberg-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "roberthouse224/project-gutenberg-mcp:1.2.0"
      ],
      "env": {
        "GUTENBERG_BASE_URL": "<gutenberg_base_url>",
        "GUTENBERG_TOOLS": "<gutenberg_tools>",
        "GUTENBERG_BOOK_ID": "<gutenberg_book_id>",
        "GUTENBERG_CHUNK_SIZE": "4096",
        "GUTENBERG_LANGUAGE": "en"
      }
    }
  }
}
§02  Environment variables
GUTENBERG_BASE_URL
required

Base URL of your Gutenberg mirror. Run the mirror from the mirror/ directory and point this at it. See the README for setup instructions.

GUTENBERG_TOOLS
required

Comma-separated list of tools to expose. Available: search_books, get_book_metadata, fetch_book_text, list_passages, get_passage

GUTENBERG_BOOK_ID

Project Gutenberg book ID to use as the default for all tools. Find IDs via search_books. Example: 2680 for Meditations by Marcus Aurelius.

GUTENBERG_CHUNK_SIZE

Size in bytes of each passage returned by get_passage.

GUTENBERG_LANGUAGE

Default ISO 639-1 language code filter for search_books. Used when the caller omits the language parameter.

§03  MCP Quality Score  ·  methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
10
§04  Alternatives in Search