Unsloth AI Documentation
About
Search and retrieve content from the Unsloth AI documentation.
Details
- Author
- jdanas
- Categories
- Search, Knowledge Base, AI
Jump to
Setup
Install Unsloth AI Documentation in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/jdanas/unsloth-mcp
Follow the installation instructions in the repository README, then restart your MCP client.
Search and retrieve content from the Unsloth AI documentation.
A simple FastMCP implementation to connect to and query Unsloth AI documentation.
This MCP (Model Context Protocol) server provides access to Unsloth AI documentation through a set of tools that can fetch and search the documentation content. It's built using FastMCP, a Python framework for creating MCP servers.
The server provides the following tools:
- search_unsloth_docs: Search the Unsloth documentation for specific topics or keywords
- get_unsloth_quickstart: Get the quickstart guide and installation instructions
- get_unsloth_models: Get information about supported models in Unsloth
- get_unsloth_tutorials: Get information about tutorials and fine-tuning guides
- get_unsloth_installation: Get detailed installation instructions
There are several ways to run the MCP server:
Search the Unsloth documentation for specific information.
result = await client.call_tool("search_unsloth_docs", {"query": "fine-tuning"})
Get the quickstart guide and basic setup information.
result = await client.call_tool("get_unsloth_quickstart", {})
Get information about models supported by Unsloth.
result = await client.call_tool("get_unsloth_models", {})
Get information about available tutorials and guides.
result = await client.call_tool("get_unsloth_tutorials", {})
result = await client.call_tool("get_unsloth_installation", {})
This server can be used with any MCP-compatible client. The server runs using the standard MCP stdio transport protocol.
To use this server with Claude Desktop, add the following to your Claude Desktop configuration:
{ "mcpServers": { "unsloth-docs": { "command": "python", "args": ["path/to/unsloth_mcp_server.py"], "cwd": "path/to/unsloth-mcp" } } }
The server can be used with any MCP client by pointing it to the server file:
from fastmcp import Client client = Client("unsloth_mcp_server.py")
unsloth-mcp/ ├── README.md # This file ├── requirements.txt # Python dependencies ├── unsloth_mcp_server.py # Main MCP server implementation └── test_client.py # Test client for testing the server
- Web Scraping: The server fetches content from the Unsloth documentation website (https://docs.unsloth.ai)
- Content Processing: Uses BeautifulSoup to parse HTML and extract relevant text content
- Search Functionality: Implements simple keyword matching to find relevant sections
- MCP Protocol: Exposes the functionality through FastMCP tools that can be called by MCP clients
- fastmcp: The FastMCP framework for creating MCP servers
- requests: For making HTTP requests to fetch documentation
- beautifulsoup4: For parsing HTML content
- The server currently performs simple keyword-based searching rather than semantic search
- It fetches content in real-time, which may be slower than cached content
- Limited to the main documentation page content (could be extended to crawl multiple pages)
- Caching: Cache documentation content to improve response times
- Multi-page Crawling: Fetch content from multiple documentation pages
- Semantic Search: Implement more sophisticated search using embeddings
- Content Indexing: Pre-index content for faster searches
- Rate Limiting: Add proper rate limiting for web requests
Feel free to submit issues or pull requests to improve the server functionality.
This project is open source. Please check the Unsloth AI documentation website terms of use when using their content.
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
An MCP server providing searchable access to multiple AI/ML SDK documentation and source code.
Fetch, convert, and search AWS documentation pages, with recommendations for related content.
Search Stack Overflow and Stack Exchange from Claude, Cursor, and other AI agents through an MCP server.
Quran-focused MCP server for ayah translation, tafsir, mutashabihat lookups, recitation playlists, and prayer times.
Search for scientific publications across ArXiv, ACL Anthology, HuggingFace Datasets, and Semantic Scholar.
Provides AI assistants with intelligent access to ML textbook content for creating accurate, source-grounded documentation.
Structural AI Search Readiness MCP. Audit, dry-run fixes, rescore, doctor. No LLM rankings.
Caesar is a free, keyless web search API for AI agents. Its remote MCP server exposes web_search (ranked results with citable provenance) and web_fetch (full pages as clean markdown), and works anonymously with no API key.
CatchAll is a web search API built for comprehensive event retrieval — not ranked results, but all matching records.
Provides web search functionality powered by the Claude API from Anthropic.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
