Content
# Book Fetch MCP
Talk to any published book in the world right inside claude (or your other MCP clients).
## Feature list
- [x] write mcp tool, test basic version
- [x] if book too long, maintain in MCP cache, and paginate through it
- [ ] use gemini 1.5 for asking questions from book, feed that response to claude (due to GINORMOUS context length)
- [ ] spawn mini-RAG engine inside the server, ingestion, chunking, reranking. maintained through to end of app lifecycle
- [ ] integrate scihub as well. FREE THE WORLD'S KNOWLEDGEEE
## Setup
- make sure you have uv installed
- install deps. `cd book-fetch && `
- add this to your `claude_desktop_config.json`
```json
{
"mcpServers": {
"book-fetcher": {
"command": "uv",
"args": [
"--directory",
"<PATH_TO_PARENT_DIR>/libgen-mcp",
"run",
"main.py"
]
}
}
}
```
Connection Info
You Might Also Like
markitdown
Python tool for converting files and office documents to Markdown.
markitdown
MarkItDown-MCP is a lightweight server for converting URIs to Markdown.
firecrawl
Firecrawl MCP Server enables web scraping, crawling, and content extraction.
Filesystem
Node.js MCP Server for filesystem operations with dynamic access control.
TrendRadar
TrendRadar: Your hotspot assistant for real news in just 30 seconds.
mempalace
The highest-scoring AI memory system ever benchmarked. And it's free.