QuantConnect PDF

Provides fast, context-aware search over QuantConnect PDFs by converting them to markdown and indexing for TF-IDF based queries.

python

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "lhstorm-mcp_server_quantconnect_docs": {
      "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"
      }
    }
  }
}

You run an MCP server that converts QuantConnect PDFs into searchable Markdown, builds a fast, context-aware index, and serves targeted excerpts to your client. This enables quick discovery of topics like backtesting, indicators, and specific API usage across the QuantConnect documentation set.

How to use

You interact with the QuantConnect PDF MCP Server through an MCP client to search documents, list available PDFs, and retrieve full content. Use the three tools to perform typical tasks: search for relevant excerpts, list all processed documents, and fetch the complete content of a chosen document. Result snippets highlight your query terms and include page numbers for easy navigation.

How to install

Prerequisites: Python 3.8 or higher and the pip package manager.

Install dependencies with pip.

pip install -r requirements.txt

Configuration and running tips

The server runs as a local MCP process. You configure a client (such as Claude Desktop) to point to the local Python process and pass environment variables that control where PDFs are stored and where converted Markdown files should be written.

Environment variables you’ll set are:

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

Start the server in a standalone test to verify it loads and begins processing PDFs.

Troubleshooting and notes

If the server has trouble loading PDFs, check that the QUANTCONNECT_PDF_FOLDER path exists and that the PDF files are readable. Look for error messages in the server output or logs.

If searches return no results initially, allow the server to finish the initial PDF processing and indexing. The cache and index are designed for incremental updates and faster startup on subsequent runs.

Advanced usage

You can manually run the PDF conversion utility to prebuild markdown files without starting the server.

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

Available tools

search_quantconnect_docs

Intelligent search through all QuantConnect documentation with TF-IDF scoring and proximity boosting. Returns excerpts with highlighted matches and page numbers.

list_quantconnect_docs

List all available PDFs in the collection with metadata and status of processing.

get_document_content

Retrieve full content from a specific document, with optional page filtering for targeted reading.

Built by

VeilStrat

AI signals for GTM teams