QuantConnect Docs

An advanced Model Context Protocol (MCP) server that provides intelligent search and retrieval capabilities for QuantConnect PDF documentation. This server converts PDFs to searchable markdown format and provides fast, context-aware search using TF-IDF scoring and proximity matching.

- Intelligent PDF Processing: Automatically converts PDFs to structured markdown with proper formatting
- Fast Search Index: Uses inverted index with TF-IDF scoring for relevant results
- Context-Aware Results: Returns relevant excerpts with highlighted matches
- Caching System: Avoids reprocessing unchanged PDFs for better performance
- Proximity Matching: Boosts results where query terms appear close together
- Three MCP Tools: Search, list documents, and retrieve full content

QuantConnectServer/ ├── server.py # Main MCP server with enhanced search ├── convert_pdfs.py # Standalone PDF conversion utility ├── requirements.txt # Python dependencies ├── README.md # This documentation ├── env/ # Python virtual environment └── quantconnect-docs/ # PDF documents and converted markdown ├── Quantconnect-Local-Platform-Python-2.pdf ├── Quantconnect-Writing-Algorithms-Python-2.pdf └── markdown/ # Auto-generated markdown files ├── .pdf_cache.json # Processing cache ├── .search_index.pkl # Search index cache └── *.md files # Converted documents

- Python 3.8 or higher
- pip package manager

- mcp- Model Context Protocol library
- PyPDF2- PDF text extraction
- asyncio- Asynchronous processing

Create a virtual environment (recommended):

python -m venv env source env/bin/activate # On Windows: env\Scripts\activate pip install -r requirements.txt

Find your Claude Desktop configuration file:

- macOS:~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:%APPDATA%\Claude\claude_desktop_config.json
- Linux:~/.config/claude/claude_desktop_config.json

Add this configuration (adjust paths to match your system):

{ "mcpServers": { "quantconnect-pdf-server": { "command": "/path/to/your/project/env/bin/python3", "args": ["/path/to/your/project/server.py"], "env": { "QUANTCONNECT_PDF_FOLDER": "/path/to/your/project/quantconnect-docs", "QUANTCONNECT_MARKDOWN_FOLDER": "/path/to/your/project/quantconnect-docs/markdown" } } } }

- QUANTCONNECT_PDF_FOLDER: Directory containing your PDF files (required)
- QUANTCONNECT_MARKDOWN_FOLDER: Directory for converted markdown files (optional, defaults toPDF_FOLDER/markdown)

export QUANTCONNECT_PDF_FOLDER="/path/to/your/pdfs" python server.py

With Claude Desktop: Restart Claude Desktop after configuration to load the MCP server

python convert_pdfs.py [pdf_folder] [markdown_folder]

- "Can you list the available QuantConnect documents?"
- "Search for information about backtesting in the QuantConnect docs"
- "What does the QuantConnect documentation say about indicators?"
- "Show me page 5 of the Local Platform documentation"

The server provides three powerful tools accessible through Claude:

Purpose: Intelligent search through all QuantConnect documentationParameters:

- query(required): Search terms or topic to find
- max_results(optional): Number of results to return (default: 5)

- TF-IDF scoring for relevance ranking
- Proximity matching for multi-word queries
- Context extraction with highlighted matches
- Returns document excerpts with page numbers

Purpose: List all available PDF documents in the collectionParameters: None

Returns: Complete catalog of processed documents with metadata

Purpose: Retrieve full content from specific documentsParameters:

- filename(required): Document name (with or without .md extension)
- page_number(optional): Specific page to retrieve

Use cases: Reading complete sections, accessing specific pages, extracting code examples

- Inverted Index: Maps words to document locations for fast lookup
- TF-IDF Scoring: Balances term frequency with document rarity
- Proximity Boosting: Enhances results where query terms appear together
- Context Extraction: Provides relevant snippets around matches

- PDF Processing Cache: Avoids reprocessing unchanged files using MD5 hashes
- Search Index Cache: Persists search index for faster startup
- Incremental Updates: Only processes new or modified PDFs

- Asynchronous Processing: Non-blocking PDF conversion and indexing
- Background Initialization: Server starts immediately while processing continues
- Efficient Storage: Markdown conversion reduces memory usage vs. raw PDF text

- Verify absolute paths in Claude Desktop configuration
- Check Python virtual environment activation
- Ensureserver.pyhas execute permissions

- ConfirmQUANTCONNECT_PDF_FOLDERpath exists
- Check PDF file permissions and readability
- Look for error messages in server output

- Wait for initial PDF processing to complete
- Check if markdown files were created successfully
- Try broader search terms

- Ensure adequate disk space for markdown files
- Check if antivirus is scanning the project folder
- Consider moving cache files to faster storage

export QUANTCONNECT_PDF_FOLDER="/path/to/pdfs" python server.py 2>&1 | tee server.log

Process all PDFs without starting the server:

python convert_pdfs.py ./quantconnect-docs ./quantconnect-docs/markdown

The search supports various query types:

- Single terms:backtesting
- Multi-word queries:custom indicator development
- Technical terms:OnData event handler
- Code concepts:Algorithm.Initialize method

Ask Claude sophisticated questions like:

"Using the QuantConnect docs, show me step-by-step how to create a custom indicator with examples" "What are all the different order types available and when should I use each one?" "Find code examples of universe selection and explain the different approaches" "Compare the local platform setup process with cloud deployment according to the documentation"

- Add new document formats: Extend the conversion system inserver.py:236
- Improve search: Enhance theSearchIndexclass for semantic search
- Add specialized tools: Create domain-specific search functions
- Performance optimization: Implement parallel processing or database storage

- v0.3.0: Enhanced search with TF-IDF scoring and proximity matching
- v0.2.0: Added caching system and background processing
- v0.1.0: Basic PDF to markdown conversion and simple search

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.

Converts QuantConnect PDF documentation into searchable markdown, enabling fast, context-aware search.

This MCP (Model Context Protocol) server provides integration with Wiki.JS for searching and listing pages from Agent Voice Response Wiki.JS instance.

Fetch, convert, and search AWS documentation pages, with recommendations for related content.

Production-ready RAG out of the box to search and retrieve data from your own documents.

Quran-focused MCP server for ayah translation, tafsir, mutashabihat lookups, recitation playlists, and prayer times.

Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.

Provides AI assistants with intelligent access to ML textbook content for creating accurate, source-grounded documentation.

一条工務店で家を建てた施主「ろれさん」のブログ記事と、YouTube/X/Instagram/Web から集めた約3,000件の家づくり Tips を横断検索できる MCP サーバ。すべての結果に出典URLが付きます。

A flexible service for searching and analyzing academic papers on arXiv.

A local server to query Bucketeer documentation, which automatically fetches and caches content from its GitHub repository.