library-mcp
This MCP server enables AI agents to search and retrieve exact, cited passages from a large corpus of public-domain books, including full-text search, book metadata, chapters, quotes, and 'ask book' Q&A. Payments are handled via x402 micropayments on Base.
README
ForgeMesh Library — Public-Domain Knowledge Base for AI Agents
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 100+ curated subject shelves over a growing corpus of 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.
Tools
| Tool | Cost | What it does |
|---|---|---|
search_literature |
$0.02 | Full-text search across the entire corpus — real passages, any book |
search_books |
$0.005 | Search the corpus by title or author substring |
get_book_metadata |
$0.002 | 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 |
$0.003 | Browse a curated category or subject shelf (gothic horror, Russian literature, detective fiction, 100+ shelves) |
book_of_the_day |
$0.001 | Deterministic daily book pick, date-seeded |
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 actively growing — it started at hundreds of books and is on a path from 17,000+ toward roughly 62,000 as more public-domain texts are indexed. 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 100+ auto-generated subject shelves 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.txthttps://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 agentshttps://library.forgemesh.io/openapi.json— OpenAPI 3.1 with x402 payment metadata, full input schemas, and worked examples for every routehttps://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
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。