Project Gutenberg MCP. Search 60k+ public domain eBooks with AI.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Project Gutenberg MCP Server connects your AI client to a public domain library containing over 60,000 free eBooks. Use this server to search for classic literature by keyword or subject using `search_gutenberg_books`, list all available works from a specific author with `search_author`, or fetch detailed metadata for any single title via `get_book_details`.
It's your AI agent's dedicated source for historical and public domain texts.
What your AI agents can do
Get book details
Retrieves specific, granular metadata for one identified book title or ID from the collection.
Search author
Searches and lists all available published works associated with a given author's name.
Search gutenberg books
Performs general searches across the entire catalog, filtering books by keywords, subjects, or titles.
Find books by keyword, title, or subject across the 60,000+ public domain titles using search_gutenberg_books.
Retrieve every available book written by a specific author in the database through the search_author tool.
Fetch IDs, languages, and detailed information for any single book using get_book_details.
Use the combined output of these tools to gather data points from several works for thematic comparison or historical context analysis.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Project Gutenberg: 3 Tools for Literary Research
Use these tools to search entire book collections, map authors' full works, or pull precise metadata records on any classic title.
019d8471get book details
Retrieves specific, granular metadata for one identified book title or ID from the collection.
019d8471search author
Searches and lists all available published works associated with a given author's name.
019d8471search gutenberg books
Performs general searches across the entire catalog, filtering books by keywords, subjects, or titles.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Project Gutenberg, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Project Gutenberg MCP Server connects your AI client directly to a public domain library holding over 60,000 free eBooks. It gives you structured access to classic literature and historical texts—it's your agent's dedicated research source for anything in the public domain.
Here’s the deal: this server doesn't just let you 'look up' books; it forces the retrieval of granular data points like unique IDs, language codes, and specific metadata. You get structured output that lets your agent do deep literary analysis, something that was a pain to pull together before.
How It Works with Your Agent
When you connect this server, your AI client can operate like it's talking to a professional digital librarian. You tell your agent what you need, and the tool handles the complex search queries against the entire catalog.
Searching the Entire Collection: Need to find books by general topic or keyword? Use search_gutenberg_books. This function performs broad searches across the whole 60,000+ title library. You can filter results by specific keywords, literary subjects, or partial titles, letting you narrow down massive collections quickly.
Listing an Author's Back Catalog: If you know a writer but not their specific book, use search_author. This tool lists every single published work the database has associated with that author’s name. It gives you a clean roster of available texts without needing to guess titles or years.
Getting Deep Details on One Title: Once you have a title or ID, you run into get_book_details. This function pulls specific, granular metadata for that single book entry. You get the unique IDs, language details, and deep information necessary to use the text in other analysis pipelines. It’s how your agent gets the full context on one piece.
Running Complex Literary Analysis
You can combine these tools to do heavy lifting. For instance, you don't have to check 60,000 books manually just to compare themes across different periods. You use search_gutenberg_books first to find several works matching a theme—say, 'sea travel.' Then, for each of those results, you run get_book_details. This gathers the unique IDs and language data points required before your agent can perform a thematic comparison or historical context analysis across multiple sources.
You might use search_author to gather all works by Dickens, then feed that list into the process above. The combination of these tools lets you pull structured data from several different books for rigorous comparison.
It’s about building a workflow where your agent doesn't just read; it collects and organizes specific facts, making deep comparative research on public domain texts straightforward.
How Project Gutenberg MCP Works
- 1 Connect your AI client (Claude, Cursor, etc.) to the Project Gutenberg MCP Server.
- 2 Tell your agent what you're looking for—maybe 'all books by Jane Austen' or 'books about philosophy'.
- 3 Your agent invokes
search_gutenberg_booksorsearch_author, and it returns structured data containing IDs, titles, and metadata that you can use immediately.
The bottom line is: your AI client turns a massive library database into conversational data points, letting you analyze literature without manual lookups.
Who Is Project Gutenberg MCP For?
Academic researchers and digital humanists who need to work with primary source materials. If your job involves tracing literary history or cross-referencing texts across eras, this is for you. It's perfect for the student drowning in research material or the content analyst needing verifiable historical data.
Uses get_book_details to pull precise metadata (like specific IDs and languages) when citing primary sources or building a corpus for study.
Runs multi-step queries, using search_gutenberg_books to identify themes across genres, then uses the results to structure large-scale literary analyses.
Asks for all available works from a major author via search_author, giving them a quick overview of an author's entire body of work.
What Changes When You Connect
- Deep Metadata Access: Need to know the exact ID or language of a specific book? Use
get_book_details. You pull precise, structured data points instead of just reading the summary card. - Author Back-Catalog Mapping: Don't track down an author's bibliography manually. Just ask your agent for all works by them;
search_authorcompiles a complete list instantly. - Broad Topic Search: Starting with a general idea, like 'Victorian mystery'?
search_gutenberg_booksscans the whole database by subject or keyword to give you starting points. - Historical Context Retrieval: Quickly compare themes across multiple classic works. The server provides enough data (via combined tool calls) to support deep comparative analysis.
- Zero Barrier Entry: It's public access, and no API key is required to start using the tools. Just connect your client and ask questions.
Real-World Use Cases
Comparing literary themes across eras
A digital humanist wants to compare how 'love' was depicted in a book from the 1800s versus one from the early 1900s. They first use search_gutenberg_books for two different subjects, then run get_book_details on both titles. The agent combines this metadata to help structure a comparative essay.
Mapping an author's career trajectory
A student researching Mark Twain needs every book he wrote that is in the public domain. They use search_author with 'Mark Twain'. The agent returns a list of titles and IDs, allowing the student to see his entire published scope at a glance.
Finding books on an obscure topic
A historian is researching early agricultural practices. They don't know the exact book title. Instead, they use search_gutenberg_books with keywords like 'early farming methods'. The agent scans by subject and presents relevant titles for review.
Verifying a book's specific details
A researcher finds an old citation but needs to confirm the exact edition ID. They use get_book_details with the known title or partial ID, and the agent pulls the verified metadata record.
The Tradeoffs
Searching for modern topics
Asking Project Gutenberg to find a book about 'AI' or 'Climate Change'. The server only holds public domain works from centuries ago.
→ This tool is strictly for classic and historical literature. If you need current information, use an AI client connected to a real-time data source instead.
Ignoring general search
The user only knows the author but assumes they must call search_author first, even if they are interested in a specific genre.
→
If you are unsure of the scope, start with search_gutenberg_books. This lets your agent filter by subject or keyword first, which often narrows down the best results before checking an author's full list.
Asking for a book ID without context
Simply asking 'Give me the details for 1342'. The agent needs to know what that number refers to (a specific format or collection).
→
Always provide context. Say, 'Using get_book_details, fetch information for book ID 1342' so the tool knows exactly which data structure to use.
When It Fits, When It Doesn't
Use this server if your research is centered on canonical literature, historical texts, or public domain content. If you need to compare themes across multiple classic titles (using search_gutenberg_books and combined metadata), this tool shines.
Don't use it if:
* You need books published in the last 50 years. You'll hit a dead end because of copyright law.
* Your goal is to find real-time or current news (use a web search tool for that).
* You only care about one title and don't need metadata—just read the summary elsewhere.
When you combine search_author with get_book_details, you build a powerful research loop: find the author, get the list of works, then drill down into the specifics of any single title.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Project Gutenberg. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 3 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Doing literary research used to mean endless database logins and copy-pasting IDs.
Before having an agent connected to Project Gutenberg, finding a comprehensive overview of a writer's work was painful. You’d check one library site for titles, then another for metadata, manually cross-referencing ISBNs or IDs until you had the full picture—all before your actual research even started.
Now, your AI agent handles that whole process. Just ask it to list all available works by an author. The server runs `search_author` and spits out a structured list of titles and metadata points instantly. It's not just reading; it's compiling data for you.
The Project Gutenberg MCP Server: Use `get_book_details` to stop guessing.
Before, if a source cited 'Book X,' and you needed confirmation of the language or the specific edition ID, you were stuck. You had to guess which database field was correct or call multiple services just to verify basic details.
With `get_book_details`, that guessing game ends. Tell your agent the book title, and it pulls a verified metadata record with IDs and languages. It's one step to get certainty on source data.
Common Questions About Project Gutenberg MCP
How do I use the search_gutenberg_books tool? +
You ask your agent for general searches, specifying keywords or subjects like 'Philosophy' or 'Victorian mystery'. The server runs search_gutenberg_books and filters the entire catalog by what you request.
Can I get all books written by a specific author using search_author? +
Yes, that's exactly what search_author does. Just provide the name, and it lists every available work in the public domain for that author.
What is the difference between search_gutenberg_books and get_book_details? +
search_gutenberg_books finds a book when you know general criteria (topic, keyword). get_book_details retrieves all specific metadata for one book once you already have its title or ID.
Does Project Gutenberg MCP Server support modern literature? +
No. This server is limited to public domain books. It won't find anything copyrighted, so stick to classic and historical titles.
How do I use the search_gutenberg_books tool without an API key? +
You don't need one. This server uses public access, so your agent connects directly via MCP. You can run searches immediately from any compatible client like Claude or Cursor.
What happens if I call get_book_details too many times? +
The service adheres to standard rate limits for external APIs. If your agent makes excessive calls in a short period, you might hit a temporary throttle. Implementing an exponential backoff mechanism is best practice.
What kind of data does search_author return? +
It returns structured metadata for every book found by that author. Expect a list containing the title, publication date, and unique Project Gutenberg ID for each entry.
Can search_gutenberg_books find books written recently? +
No. The scope of this server is limited to public domain works, which are classic texts whose copyright has expired. You won't find modern or contemporary literature here.
Can I search for books by William Shakespeare? +
Yes! Use the search_author tool with the name 'Shakespeare'. It will return a list of his famous plays and sonnets available on Project Gutenberg.
How do I find books about a specific subject like 'History'? +
Use the search_books tool and include the subject in your query. Your agent will search the entire catalog for titles matching that theme.
Can I get the full text of a book directly? +
The current server focuses on metadata and discovery. You can retrieve the official Project Gutenberg ID for any book, which can be used to find the full text on their website.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
OpenFarm Agriculture
Access crowdsourced agricultural data — search for crops, growing guides, and planting instructions.
Thesaurus API
Search synonyms and antonyms — audit linguistics via AI.
Quotable API
Access thousands of quotes — audit authors and tags via AI.
You might also like
ScrapingAnt
Extract web data reliably with rotating proxies, headless Chrome rendering, and CAPTCHA solving built into every request.
PropelAuth (B2B Authentication)
Manage B2B authentication, users, and organizations via PropelAuth — handle user provisioning, org management, and API keys directly from your AI agent.
Jibble
Track time, attendance, and projects via Jibble API.