Project Gutenberg MCP
Let your agent search Project Gutenberg, pull book metadata, and fetch passages for research, writing, and training context without manual downloads.
Overview
Project Gutenberg MCP is an MCP server for the Idea phase that searches a Gutenberg mirror, returns book metadata, and retrieves text passages for agent-led research.
What is this MCP server?
- Five configurable tools: search_books, get_book_metadata, fetch_book_text, list_passages, get_passage
- Requires a self-hosted Gutenberg mirror via GUTENBERG_BASE_URL such as http://localhost:8080
- Docker OCI package roberthouse224/project-gutenberg-mcp:1.2.0 with stdio MCP transport
- GUTENBERG_TOOLS lets you expose only the book operations your agent needs
- Server version 1.2.0
- Five available tools: search_books, get_book_metadata, fetch_book_text, list_passages, get_passage
- OCI image identifier roberthouse224/project-gutenberg-mcp:1.2.0
What problem does it solve?
Builders waste hours manually downloading and chunking public-domain books when their agent could query a local mirror if only MCP exposed search and passage tools.
Who is it for?
Indie creators researching public-domain corpora, building reading agents, or prototyping RAG over classic literature with a mirror they control.
Skip if: Projects that need commercial licensed ebooks, a zero-setup cloud corpus, or agents that cannot run Docker and a local mirror.
What do I get? / Deliverables
After you run a Gutenberg mirror and register the MCP server, your agent can search titles, inspect metadata, and pull passages for summaries, apps, or content pipelines.
- Agent-accessible search and metadata over your Gutenberg mirror
- Passage-level text retrieval for summaries, quoting, and downstream content or RAG workflows
Recommended MCP Servers
Journey fit
Public-domain book access supports early discovery and reference gathering before you commit to product scope or heavy backend work. Research is the canonical shelf because the tools center on search, metadata, and passage retrieval for reading and citation, not deployment or growth analytics.
How it compares
Research-oriented book mirror MCP, not a DeFi proxy or append-only operations log.
Common Questions / FAQ
Who is project-gutenberg-mcp for?
It is for solo builders and researchers who want agents to query Project Gutenberg content through a self-hosted mirror with structured MCP tools.
When should I use project-gutenberg-mcp?
Use it during idea and research work when you need searchable public-domain books and passage-level retrieval before or alongside product build.
How do I add project-gutenberg-mcp to my agent?
Start the mirror from the package mirror directory, set GUTENBERG_BASE_URL and GUTENBERG_TOOLS, run roberthouse224/project-gutenberg-mcp:1.2.0 via Docker, and add the stdio MCP server to your client.