How do I install the gutenberg mcp server?

Use a recorded configuration for your client, replace example credential values and paths, and verify the documented runtime. Restart or reconnect the client, then inspect the available tools.

What credentials does it need?

It reads `MCP_TRANSPORT_TYPE`, `MCP_LOG_LEVEL`, `GUTENDEX_BASE_URL`, `GUTENBERG_TEXT_BASE_URL` from the environment. Store these in your client's env block or a secrets manager — never commit them to a repository — and grant the narrowest scope that still covers your use case.

SSyncDev

Start a project

Gutenberg MCP Server

MCP server for Project Gutenberg — 75,000+ public-domain ebooks with full plain-text retrieval.

Remote serverstreamable-http

What is the Gutenberg MCP Server?

MCP server for Project Gutenberg — 75,000+ public-domain ebooks with full plain-text retrieval.

What it actually does

Declarative tool definitions — single file per tool, framework handles registration and validation
Unified error handling — handlers throw, framework catches, classifies, and formats with recovery hints
Pluggable auth: none, jwt, oauth
Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
Structured logging with optional OpenTelemetry tracing
STDIO and Streamable HTTP transports

Configuration

Bun v1.3.11 or higher (or Node.js v24+). - No API key required — Project Gutenberg data is freely available.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

Tool	What it does
gutenberg_search_books	Search the Gutenberg catalog by title, author, topic, language, or author lifespan — returns popularity-ordered results with IDs ready for follow-up calls
gutenberg_get_book	Fetch complete metadata for a book by ID — full formats map, translators, editors, subjects, bookshelves, copyright status, and the has_plain_text flag
gutenberg_get_text	Retrieve the plain-text content of a book, stripped of license boilerplate, with offset/limit chunking for context-budget management
gutenberg_browse_popular	Browse the most-downloaded books, optionally filtered by language or topic — useful as a discovery entry point

How to install the Gutenberg MCP Server

{
  "mcpServers": {
    "gutenberg-mcp-server": {
      "type": "streamable-http",
      "url": "https://gutenberg.caseyjhand.com/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

Bun v1.3.11 or higher (or Node.js v24+). - No API key required — Project Gutenberg data is freely available.

Variable	Description	Required
MCP_TRANSPORT_TYPE	Configuration value read at startup.	Optional
MCP_LOG_LEVEL	Configuration value read at startup.	Optional
GUTENDEX_BASE_URL	Endpoint or connection string the server talks to.	Yes
GUTENBERG_TEXT_BASE_URL	Endpoint or connection string the server talks to.	Yes

Example prompts to try

“Use Gutenberg to gutenberg search books.”
“Use Gutenberg to gutenberg get book.”
“Use Gutenberg to gutenberg get text.”

Frequently asked questions

MCP server for Project Gutenberg — 75,000+ public-domain ebooks with full plain-text retrieval. Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.