Skip to main content
Glama

ForgeMesh Library — Public-Domain Knowledge Base for AI Agents

M8ven Score mcpservers.org

A ForgeMesh Labs product.

A paid public-domain knowledge base, built for agents. Full-text search, book metadata, chapters, notable quotes, flagship "ask this book a question" retrieval, and 280+ curated subject shelves over 61,000+ public-domain books — no license, no API key, no account. Pay per call in USDC on Base via x402.

Retrieval only: every answer is a real, cited passage pulled from the indexed text. Nothing here is LLM-generated or summarized — that makes it safe to cite for tutoring agents, reading apps, quiz/curriculum generators, and any workflow where a hallucinated quote is worse than no quote.

Quick start (Claude Desktop / Claude Code / any MCP client)

{
  "mcpServers": {
    "library": {
      "command": "npx",
      "args": ["-y", "@forgemeshlabs/library-mcp"],
      "env": {
        "WALLET_PRIVATE_KEY": "0x..."
      }
    }
  }
}

WALLET_PRIVATE_KEY is a dedicated low-balance Base wallet for x402 micropayments — never your primary wallet. $1 of USDC buys dozens to hundreds of calls depending on the route.

Related MCP server: open-public-domain

Requirements

Node.js 20+ and a dedicated, low-balance Base wallet funded with USDC. The server refuses to sign for any payee other than the Library wallet, any network other than Base mainnet, any asset other than USDC, or any amount over the cap ($0.02 per call, $10 per session). The env vars X402_MAX_PRICE_USD and X402_SESSION_BUDGET_USD can only lower those caps. Requests are same-origin, time out after 60 seconds, are capped at 2 MB, and never follow redirects.

Tools

Tool

Cost

What it does

search_literature

$0.02

Full-text search (1-8 words) across the entire corpus — real passages, any book; no match = 404, not charged

search_books

$0.005

Search the corpus by title or author substring

get_book_metadata

$0.005

Title, author, year, subjects, bookshelves, chapter range for a book_id

get_chapter

$0.005

Full text of one chapter by book_id + chapter number

get_quotes

$0.005

Notable passages from a book, optionally themed

ask_book

$0.01

Ask a flagship book (Moby Dick, the Republic, Sherlock Holmes...) a question, get cited passages back

browse_shelf

$0.005

Browse a curated category or subject shelf (gothic horror, Russian literature, detective fiction, 280+ shelves)

book_of_the_day

$0.005

Deterministic daily book pick, date-seeded

library_card

$0.005

Mint a soulbound Reader's Card NFT on Base mainnet to the paying wallet (payment settles first, then mint; one card per wallet)

Refusals (404 no match, 4xx validation) are reported with their HTTP status and charged state. Prices are set by the live service and may change — the actual charge always comes from the x402 402 challenge at call time, not this table.

Who this is for

Built for education-safe agent use cases:

  • Tutoring agents that need a real quote, not a paraphrase

  • Reading apps and book-club bots

  • Quiz and curriculum generators that cite public-domain source text

  • Any agent that needs a large, cheap, license-free text corpus without hitting a rate-limited free API

Nothing here requires an account, an API key, or a license negotiation — the entire corpus is public domain, drawn in part from the Project Gutenberg collection. Not affiliated with or endorsed by Project Gutenberg.

Corpus size

The corpus is 61,000+ public-domain books (~62,000 target) and still growing. Don't hardcode a book count anywhere downstream of this server; ask search_books or search_literature and let the live index answer.

Flagship books (ask_book)

Alice in Wonderland, Art of War, Count of Monte Cristo, Crime and Punishment, Don Quixote, Dracula, Frankenstein, Great Expectations, Grimms' Fairy Tales, Jane Eyre, Meditations (Marcus Aurelius), Moby-Dick, The Picture of Dorian Gray, Pride and Prejudice, Sherlock Holmes, The Iliad, The Odyssey, The Republic, The Time Machine, Tom Sawyer, Treasure Island, Walden, War and Peace, Wuthering Heights.

Any other book: use search_literature or search_books + get_chapter/get_quotes instead — the flagship ask_book routes are hand-curated, the rest of the corpus is reachable through search.

Shelves (browse_shelf)

10 hand-picked categories (adventure, children's classics, classic literature, economics & politics, gothic horror, history, philosophy, poetry, science & nature, Shakespeare & drama) plus 270+ auto-generated subject shelves (book counts generated from the live index; an unknown shelf is a free 404) drawn from real Gutenberg subjects/bookshelves metadata (gothic fiction, Russian literature, detective fiction, banned books lists, and more).

The full, current shelf catalog is free to browse — no payment, no tool call required:

  • https://library.forgemesh.io/llms.txt

  • https://library.forgemesh.io/openapi.json

How payment works

No signup, no API key, no subscription. The first request to any tool returns an HTTP 402 challenge; this MCP server signs a USDC payment authorization (EIP-3009) and retries automatically. The result lands in the same response, with the on-chain settlement details under _payment when available.

Direct API

Prefer raw HTTP? The full agent-readable surface:

  • https://library.forgemesh.io/llms.txt — one-page summary for agents

  • https://library.forgemesh.io/openapi.json — OpenAPI 3.1 with x402 payment metadata, full input schemas, and worked examples for every route

  • https://library.forgemesh.io/.well-known/x402.json — x402 discovery manifest

FAQ

Is this LLM-generated? No. Every response is retrieval over a local full-text index of real books. The method field in every response says so explicitly.

Do I need an account or API key? No. x402 payments are the only credential.

What chain and token? USDC on Base mainnet (eip155:8453).

Can I use this for tutoring or curriculum content? Yes — that's the intended use. Retrieval-only, cited-passage answers are education-safe in a way generated summaries aren't.


Built by ForgeMesh Labs · Powered by the x402 protocol · MIT License

Available Tools

8 tools
ask_bookA

Ask a natural-language question about one of the flagship books and get back the most relevant passages from the book itself, with chapter/location citations. Retrieval only — never a generated summary. Pass any recognizable name for "book" (e.g. "Moby Dick", "the Odyssey") — it resolves to the matching route. Available flagship books: alice in wonderland, art of war, count of monte cristo, crime and punishment, don quixote, dracula, frankenstein, great expectations, grimms fairy tales, jane eyre, meditations, moby dick, picture of dorian gray, pride and prejudice, sherlock holmes, iliad, odyssey, republic, time machine, tom sawyer, treasure island, walden, war and peace, wuthering heights. Costs $0.01 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: book (required), question (required), limit.

book_of_the_dayA

Deterministic daily book pick from the indexed corpus, date-seeded so every caller gets the same answer on the same UTC day. Optional date override for backfill. Costs $0.001 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: date.

browse_shelfA

Browse a curated category/subject shelf: 10 hand-picked categories (adventure, childrens-classics, classic-literature, economics-and-politics, gothic-horror, history, philosophy, poetry, science-and-nature, shakespeare-and-drama) plus 100+ auto-generated shelves drawn from real Gutenberg subjects/bookshelves (e.g. 'gothic-fiction', 'russian-literature', 'detective-fiction'). Returns a ranked list of books with book_id for drill-down. Full shelf catalog is discoverable free at https://library.forgemesh.io/llms.txt. Costs $0.003 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: shelf (required).

get_book_metadataA

Full metadata for one indexed book by book_id: title, author, year, subjects, bookshelves, download rank, chunk count, and detected chapter range. Use search_books first to find a book_id. Costs $0.002 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: book_id (required).

get_chapterA

Full text of one chapter from an indexed book by book_id and chapter number. Chapter 0 is front matter before the first detected heading. Use get_book_metadata for the valid chapter range. Costs $0.005 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: book_id (required), chapter (required).

get_quotesA

Notable passages from one indexed book by book_id. Pass an optional theme to full-text search within that book, or omit it for a sample of short dialogue-bearing lines. Costs $0.005 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: book_id (required), limit, theme.

search_booksA

Search the indexed public-domain book corpus by title or author substring, e.g. 'Dickens' or 'Frankenstein'. Returns matching books ranked by historical popularity with book_id for drill-down into metadata, chapters, quotes, or full-text search. Costs $0.005 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: query (required), limit.

search_literatureA

PREMIUM full-text search across the entire indexed public-domain corpus (17k+ books and growing). Returns the most relevant passages from ANY book, ranked by relevance, with title/author citations. Retrieval only — real cited passages, never LLM-generated or summarized. Costs $0.02 via x402 (requires WALLET_PRIVATE_KEY, USDC on Base).

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 8 tools

    Disambiguation5/5

    Each tool targets a distinct resource and action: search_books finds books by metadata, search_literature retrieves passages corpus-wide, get_book_metadata provides details, get_chapter fetches a chapter, get_quotes extracts notable lines, ask_book answers questions from flagship books, browse_shelf explores categories, and book_of_the_day returns a daily pick. The descriptions clearly differentiate scope and output, leaving no ambiguity about when to use which tool.

    Naming Consistency4/5

    The majority of tool names follow a consistent verb_noun pattern (search_*, get_*, ask_book, browse_shelf). The only deviation is book_of_the_day, which is a noun phrase rather than a verb imperative, but it remains descriptive and predictable within the set.

    Tool Count5/5

    With 8 tools, the server is well-scoped for a public-domain library. Each tool covers a distinct capability—discovery, access, analysis, and daily picks—without unnecessary redundancy or overwhelming volume.

    Completeness5/5

    The tool surface provides complete read-only lifecycle coverage: users can discover books (search_books, browse_shelf, book_of_the_day), retrieve content (get_chapter, get_quotes), get metadata (get_book_metadata), and perform advanced retrieval (search_literature, ask_book). No obvious gaps exist for a curated library corpus.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI models to search and retrieve bibliographic and digitized records from Swiss academic libraries (swisscovery, e-rara, e-periodica, e-manuscripta) via open protocols without requiring API keys.
      16
      43 PyPI
      1
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables browsing, searching, and quote verification of a local ebook library via MCP, providing deterministic RAG with no embeddings or network.
      6
      2
      MIT