Connects Claude to Project Gutenberg's public domain catalog through a self-hosted mirror. Exposes five tools: search books by title or author, fetch metadata, download full text, list fixed-size passages, and retrieve specific passages. You'll need to run the included mirror server locally since Project Gutenberg blocks automated access to their main site. Useful for literary analysis, quote extraction, or building applications that reference classic texts. Configure it with a book ID to default to a specific work, or enable search to let Claude discover titles on the fly. Ships with Docker Compose setup that runs both mirror and MCP server together.
An MCP server for reading books from Project Gutenberg.
Project Gutenberg's robot access policy states that the site is intended for human users only. Automated access may result in your IP being blocked.
To use this MCP server you must run your own mirror. Project Gutenberg explicitly supports and encourages mirroring — see their mirroring guide for details.
This repository includes a ready-to-run mirror server in the mirror/ directory.
The mirror server downloads the Project Gutenberg catalog on startup (~5 MB compressed) and caches book files locally on first access. It exposes the URL structure that this MCP server expects.
Runs the mirror and MCP server together. The MCP server is exposed on HTTP at port 8081.
docker compose up
The mirror is available at http://localhost:8080 and the MCP server at http://localhost:8081/mcp.
Build and start just the mirror, then connect an MCP client via stdio.
task build:mirror
task start:mirror
The mirror runs at http://localhost:8080. Example MCP client config (stdio):
{
"mcpServers": {
"project-gutenberg-mcp": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "GUTENBERG_BASE_URL=http://host.docker.internal:8080",
"-e", "GUTENBERG_TOOLS=search_books,get_book_metadata,list_passages,get_passage",
"roberthouse224/project-gutenberg-mcp"
]
}
}
}
All configuration is via environment variables.
| Variable | Required | Description |
|---|---|---|
GUTENBERG_BASE_URL | Yes | Base URL of your Gutenberg mirror (see Mirror Setup above) |
GUTENBERG_TOOLS | Yes | Comma-separated list of tools to expose (see below) |
GUTENBERG_BOOK_ID | No | Project Gutenberg book ID to use as default |
GUTENBERG_CHUNK_SIZE | No | Passage size in bytes (default: 4096) |
GUTENBERG_LANGUAGE | No | Default ISO 639-1 language code for search_books (default: en) |
| Tool | Description |
|---|---|
search_books | Search for books by title or author |
get_book_metadata | Fetch metadata (title, authors, formats) for a book |
fetch_book_text | Download the full plain text of a book |
list_passages | List fixed-size passage keys for a book |
get_passage | Fetch a specific passage by its key |
When GUTENBERG_BOOK_ID is set, tools that take a book ID will use it as the default. When it is not set, include search_books in your tools list so an agent can discover IDs first.
GUTENBERG_BASE_URL=http://localhost:8080 \
GUTENBERG_BOOK_ID=2680 \
GUTENBERG_TOOLS=get_book_metadata,list_passages,get_passage \
./project-gutenberg-mcp --transport stdio
GUTENBERG_BASE_URL=http://localhost:8080 \
GUTENBERG_BOOK_ID=2680 \
GUTENBERG_TOOLS=get_book_metadata,list_passages,get_passage \
./project-gutenberg-mcp --transport http --addr :8081
# MCP server
docker pull roberthouse224/project-gutenberg-mcp:1.2.0
# Mirror
docker pull roberthouse224/gutenberg-mirror:1.2.0
Both Dockerfiles use Docker Hardened Images (DHI) for enhanced security. Building requires authentication to Docker Hub:
docker login
Then build:
# Build MCP server
docker build -t project-gutenberg-mcp .
# Build mirror
docker build -f mirror/Dockerfile -t gutenberg-mirror ./mirror
# HTTP
docker run -p 8081:8081 \
-e GUTENBERG_BASE_URL=http://host.docker.internal:8080 \
-e GUTENBERG_BOOK_ID=2680 \
-e GUTENBERG_TOOLS=get_book_metadata,list_passages,get_passage \
roberthouse224/project-gutenberg-mcp --transport http --addr :8081
# stdio
docker run -i --rm \
-e GUTENBERG_BASE_URL=http://host.docker.internal:8080 \
-e GUTENBERG_BOOK_ID=2680 \
-e GUTENBERG_TOOLS=get_book_metadata,list_passages,get_passage \
roberthouse224/project-gutenberg-mcp
# Create a named volume for cache persistence
docker volume create gutenberg-cache
# Run mirror (serves on http://localhost:8080)
docker run -d \
-p 8080:8080 \
-v gutenberg-cache:/data \
--name gutenberg-mirror \
roberthouse224/gutenberg-mirror:1.2.0
Both images support linux/amd64 and linux/arm64 architectures. To build and push multi-arch images:
# Create a builder instance
docker buildx create --name multiarch --use
# Build and push MCP server
docker buildx build \
--platform linux/amd64,linux/arm64 \
-t roberthouse224/project-gutenberg-mcp:1.2.0 \
-t roberthouse224/project-gutenberg-mcp:latest \
--push \
.
# Build and push mirror
docker buildx build \
--platform linux/amd64,linux/arm64 \
-t roberthouse224/gutenberg-mirror:1.2.0 \
-t roberthouse224/gutenberg-mirror:latest \
--push \
-f mirror/Dockerfile \
./mirror
{
"mcpServers": {
"project-gutenberg-mcp": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "GUTENBERG_BASE_URL=http://host.docker.internal:8080",
"-e", "GUTENBERG_BOOK_ID=2680",
"-e", "GUTENBERG_TOOLS=get_book_metadata,list_passages,get_passage",
"roberthouse224/project-gutenberg-mcp:1.2.0"
]
}
}
}
task build # outputs to build/project-gutenberg-mcp
task build:mirror # outputs to mirror/build/mirror
task test
A few useful IDs:
| Book | ID |
|---|---|
| Meditations — Marcus Aurelius | 2680 |
| The Republic — Plato | 1497 |
| Thus Spoke Zarathustra — Nietzsche | 1998 |
| Moby Dick — Melville | 2701 |
| Pride and Prejudice — Austen | 1342 |
GUTENBERG_BASE_URL*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*Comma-separated list of tools to expose. Available: search_books, get_book_metadata, fetch_book_text, list_passages, get_passage
GUTENBERG_BOOK_IDProject 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_SIZEdefault: 4096Size in bytes of each passage returned by get_passage.
GUTENBERG_LANGUAGEdefault: enDefault ISO 639-1 language code filter for search_books. Used when the caller omits the language parameter.
com.mcparmory/google-search
io.github.pipeworx-io/brave-search
marcopesani/mcp-server-serper
brave/brave-search-mcp-server
com.mcparmory/google-search-console
acamolese/google-search-console-mcp