Public Hosted Server: https://gutenberg.caseyjhand.com/mcp

Tools

Four tools for searching and reading Project Gutenberg's public-domain library:

gutenberg_search_books

Search the Project Gutenberg catalog of 78,000+ public-domain books.

• Full-text search against titles and author names (space-separated words, case-insensitive)

• Topic filter matches subject headings and bookshelf categories

• Language filter by ISO 639-1 two-character codes (e.g., ["en"], ["fr", "de"])

• Author lifespan range filter via author_year_start / author_year_end

• Sort by popularity (download count), or by Gutenberg ID ascending/descending

• Batch lookup by known ID list via ids parameter

• Paginated — up to 32 books per page; use totalCount to determine total pages

• Each result includes has_plain_text to indicate whether gutenberg_get_text will work

gutenberg_get_book

Fetch complete metadata for a single Project Gutenberg book.

• Returns the full formats map (MIME type → download URL) including plain text, HTML, EPUB, and cover image

• Includes translators and editors alongside authors, each with birth/death years

• has_plain_text flag confirms whether a UTF-8 plain-text format is available

• media_type distinguishes readable text books from audio recordings

• Use this before gutenberg_get_text to confirm text availability and inspect the formats map

gutenberg_get_text

Retrieve the plain-text content of a Project Gutenberg book, stripped of license boilerplate.

• Strips the standard Gutenberg license header and footer — response contains only the literary work

• Offset/limit chunking for long works: novels routinely run 500 KB–2 MB; read in manageable chunks without loading the whole file

• Response includes totalChars, offset, length, and remainingChars for precise pagination

• Paragraph-boundary trimming: actual returned length may be slightly less than limit — use length (not limit) to compute the next offset

• Prefers UTF-8 plain text; falls back to an HTML edition converted to text

• Refuses audio books (media_type "Sound") with a clear recovery hint

• provenance field carries the Gutenberg ID, title, and license URL for attribution

gutenberg_browse_popular

Browse the most-downloaded Project Gutenberg books.

• Returns up to 32 titles ordered by download count (most popular first)

• Optionally filter by language (ISO 639-1 codes) and/or topic keyword

• Useful as a discovery entry point: "what are the most popular classics in French?"

• totalInCatalog provides full context — "top 20 of 60,000"

Features

Built on @cyanheads/mcp-ts-core:

• 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

Project Gutenberg integration:

• Catalog search and metadata via Gutendex — an unofficial but stable JSON API over the Gutenberg dataset

• Full plain-text retrieval from a Project Gutenberg content mirror (permits automated access) with transparent UTF-8/HTML fallback

• Tenant-scoped text caching: book text is fetched once per tenant and served from cache for subsequent chunk reads

• No API key required — Project Gutenberg data is freely available; no registration needed

Agent-friendly output:

• has_plain_text flag on every search/browse result so agents can pre-filter before attempting text retrieval

• Precise chunking contract: offset, length, totalChars, remainingChars, hasMore on every gutenberg_get_text response for reliable sequential reads

• provenance field on every text response for attribution

• Discriminated sourceFormat field (text/plain; charset=utf-8, text/html) so agents know the fidelity of the text

Getting started

Public Hosted Instance

A public instance is available at https://gutenberg.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

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

Self-Hosted / Local

No API key required. Add the following to your MCP client configuration file:

{
  "mcpServers": {
    "gutenberg-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/gutenberg-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "gutenberg-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/gutenberg-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "gutenberg-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/gutenberg-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.3.0 or higher (or Node.js v24+).

• No API key required — Project Gutenberg data is freely available.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/gutenberg-mcp-server.git

2. Navigate into the directory:

cd gutenberg-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env if you need to override any defaults

Configuration

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec

Docker

docker build -t gutenberg-mcp-server .
docker run --rm -p 3010:3010 gutenberg-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/gutenberg-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md / AGENTS.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic

• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage

• Register new tools via the entry arrays in src/index.ts

• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.

Data from Project Gutenberg is in the public domain. Catalog metadata sourced from Gutendex (MIT license).