The only SEC EDGAR library built from the ground up for AI agents and LLMs. Extract financial data in 3 lines of code instead of 100+. Production-ready MCP server included.
Built with AI-assisted development • 3-10x faster velocity • Support this project
EdgarTools is the fastest, most powerful open-source library for SEC EDGAR data extraction. Built for financial analysts, data scientists, and AI developers who need reliable, production-ready access to SEC filings.
# 1. Install
pip install edgartools
# 2. Set your identity (required by SEC regulations)
from edgar import *
set_identity("your.name@example.com")
# 3. Get company financials in 1 line
balance_sheet = Company("AAPL").get_financials().balance_sheet()
# 4. Explore with interactive documentation
company = Company("MSFT")
# 5. Or explore insider transactions
filings = company.get_filings(form="4")
form4_filing = filings[0]
form4 = form4_filing.obj()|
Financial Statements (XBRL)
Fund Holdings (13F)
Company Dataset & Reference Data
Insider Transactions
|
Filing Intelligence
Performance & Reliability
Developer Experience
|
EdgarTools provides AI Skills that enable Claude and other AI assistants to perform sophisticated SEC filing analysis. Once configured, you can ask Claude questions like:
- "Compare Apple and Microsoft's revenue growth rates over the past 3 years"
- "Which Tesla executives sold more than $1 million in stock in the past 6 months?"
- "Find all technology companies that filed proxy statements with executive compensation changes"
Claude will write the Python code, execute it, and explain the results - all powered by EdgarTools.
Setup Instructions
Install the EdgarTools skill for Claude Code or Claude Desktop:
pip install "edgartools[ai]"
python -c "from edgar.ai import install_skill; install_skill()"This adds SEC analysis capabilities to Claude, including 3,450+ lines of API documentation, code examples, and form type reference.
Run EdgarTools as an MCP server for Claude Code or Claude Desktop:
pip install "edgartools[ai]"
python -m edgar.aiAdd to Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"edgartools": {
"command": "python",
"args": ["-m", "edgar.ai"],
"env": {
"EDGAR_IDENTITY": "Your Name your.email@example.com"
}
}
}
}See AI Integration Guide for complete documentation.
I build and maintain EdgarTools solo using AI-assisted development. Your support directly funds the Claude Max subscription that makes this extraordinary velocity possible.
|
Releases 1 every 2.5 days |
Commits 5.4 per day |
Velocity vs traditional dev |
Not Weeks for major features |
| Feature | Traditional Estimate | With AI | Speedup |
|---|---|---|---|
| XBRL Period Selection | 3-4 weeks | 5 days | 7x faster |
| MCP Workflow Tools | 2-3 weeks | 2 days | 10x faster |
| HTML Parsing Rewrite | 2 weeks | 3 days | 4x faster |
| Standardized Concepts API | 2 weeks | 2-3 days | 5x faster |
What your support enables:
Claude Max subscription (AI agents that write, test, and document code)
Continued 3-10x development velocity (features in days, not weeks)
Rapid response to SEC format changes and bug reports
New features based on community needs
Free access for everyone, forever (no API keys, no rate limits)
Alternative ways to support:
Star the repo on GitHub
Report bugs and contribute fixes
Improve documentation
Answer questions in Discussions
Share EdgarTools with colleagues
Corporate users: If your organization depends on EdgarTools for SEC compliance or regulatory reporting, GitHub Sponsors offers strategic sponsorship options designed for mission-critical dependencies.
- GitHub Issues - Bug reports and feature requests
- Discussions - Questions and community discussions
We welcome contributions from the community! Here's how you can help:
- Code: Fix bugs, add features, improve documentation
- Examples: Share interesting use cases and examples
- Feedback: Report issues or suggest improvements
- Spread the Word: Star the repo, share with colleagues
See our Contributing Guide for details.
EdgarTools is distributed under the MIT License

