MCP 服务器

EdgarTools MCP

Enables LLMs to download, parse, and analyze SEC EDGAR filings, including 10-K/Q reports, XBRL financial statements, and insider trading data. It provides structured access to institutional holdings, corporate events, and financial facts for comprehensive investment research.

README

<h1 align="center">EdgarTools - Python Library for SEC EDGAR Filings</h1> <h3 align="center">The AI Native Python library for SEC EDGAR Data</h3>

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 • <a href="#-support-ai-powered-development">Support this project</a>

EdgarTools is a Python library for downloading and analyzing SEC EDGAR filings. Extract 10-K, 10-Q, 8-K reports, parse XBRL financial statements, and access insider trading data (Form 4) with a simple Python API. Free and open-source.

EdgarTools SEC filing data extraction demo

Why EdgarTools?

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.

<table align="center"> <tr> <td align="center" width="33%"> <img src="docs/images/icons/icon-speed.svg" width="80" alt="Lightning Fast"> Lightning Fast 10-30x faster than alternatives Optimized with lxml & PyArrow </td> <td align="center" width="33%"> <img src="docs/images/icons/icon-ai.svg" width="80" alt="AI Native"> AI Native Built-in MCP server for Claude LLM-optimized text extraction </td> <td align="center" width="33%"> <img src="docs/images/icons/icon-quality.svg" width="80" alt="Data Quality"> Production Quality 1000+ tests, type hints Battle-tested by analysts </td> </tr> <tr> <td align="center" width="33%"> <img src="docs/images/icons/icon-xbrl.svg" width="80" alt="XBRL Support"> XBRL Native Full XBRL standardization Cross-company comparisons </td> <td align="center" width="33%"> <img src="docs/images/icons/icon-data.svg" width="80" alt="Rich Data"> Rich Data Objects Smart parsing for every form Pandas-ready DataFrames </td> <td align="center" width="33%"> <img src="docs/images/icons/icon-community.svg" width="80" alt="Open Source"> Open Source MIT license, community-driven Transparent & auditable </td> </tr> </table>

How It Works

# Install the SEC EDGAR Python library
pip install edgartools

# Set your identity (required by SEC regulations)
from edgar import *
set_identity("your.name@example.com")

# Get SEC 10-K, 10-Q filings and XBRL financial statements
balance_sheet = Company("AAPL").get_financials().balance_sheet()

# Access any company's SEC filings
company = Company("MSFT")

# Parse Form 4 insider trading transactions
filings = company.get_filings(form="4")
form4_filing = filings[0]
form4 = form4_filing.obj()

Apple SEC Form 4 insider transaction data extraction with Python

Use Cases

Analyze 13F Institutional Holdings & Hedge Fund Portfolios

Track what hedge funds and institutional investors own by parsing SEC 13F filings. EdgarTools extracts complete portfolio holdings with position sizes, values, and quarter-over-quarter changes.

from edgar import get_filings
thirteenf = get_filings(form="13F-HR")[0].obj()
thirteenf.holdings  # DataFrame of all portfolio positions

Track Insider Trading with SEC Form 4

Monitor insider buying and selling activity from SEC Form 4 filings. See which executives are purchasing or selling shares, option exercises, and net position changes.

company = Company("TSLA")
form4 = company.get_filings(form="4")[0].obj()
form4.transactions  # Insider buy/sell transactions

Extract Financial Statements from 10-K and 10-Q Filings

Get income statements, balance sheets, and cash flow statements from SEC annual and quarterly reports. Data is parsed from XBRL with standardized labels for cross-company comparison.

financials = Company("MSFT").get_financials()
financials.balance_sheet()   # Balance sheet with all line items
financials.income_statement()  # Revenue, net income, EPS

Parse 8-K Current Reports for Corporate Events

Access material corporate events as they happen -- earnings releases, acquisitions, executive changes, and more. EdgarTools parses 8-K filings into structured items with full text extraction.

eightk = get_filings(form="8-K")[0].obj()
eightk.items  # List of reported event items

Query XBRL Financial Data Across Companies

Access structured XBRL financial facts for any SEC filer. Query specific line items like revenue or total assets over time, and compare across companies using standardized concepts.

facts = Company("AAPL").get_facts()
facts.to_pandas("us-gaap:Revenues")  # Revenue history as DataFrame

Comprehensive SEC Data Access

Financial Statements (XBRL)

Balance Sheets, Income Statements, Cash Flows
Individual line items via XBRL tags
Multi-period comparisons with comparative periods
Standardized cross-company data
Automatic unit conversion
Metadata columns (dimensions, members, units)
Complete dimensional data support

Fund Holdings (13F)

Complete 13F filing history
Portfolio composition analysis
Position tracking over time
Ownership percentages
Value calculations

Company Dataset & Reference Data

Industry and state filtering
Company subsets with metadata
Standardized industry classifications
SEC ticker/CIK lookups
Exchange information

Insider Transactions

Form 3, 4, 5 structured data
Transaction history by insider
Ownership changes
Grant and exercise details
Automatic parsing

</td> <td width="50%" valign="top">

Filing Intelligence

Any form type (10-K, 10-Q, 8-K, S-1, etc.)
Complete history since 1994
Smart data objects for each form
Automatic HTML to clean text
Section extraction (Risk Factors, MD&A)

Performance & Reliability

10-30x faster than alternatives
Configurable rate limiting (enterprise mirrors supported)
Custom SEC data sources (corporate/academic mirrors)
Smart caching (30-second fresh filing cache)
Robust error handling
SSL verification with fail-fast retry
Type hints throughout
Enterprise configuration →

Developer Experience

Intuitive, consistent API
Pandas DataFrame integration
Rich terminal output
Comprehensive documentation
1000+ tests

</td> </tr> </table>

EdgarTools supports all SEC form types including 10-K annual reports, 10-Q quarterly filings, 8-K current reports, 13F institutional holdings, Form 4 insider transactions, proxy statements (DEF 14A), and S-1 registration statements. Parse XBRL financial data, extract text sections, and convert filings to pandas DataFrames.

Comparison with Alternatives

Feature	EdgarTools	sec-api (paid)	OpenEDGAR	Manual Scraping
AI/MCP Integration	<img src="docs/images/icons/compare-check.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">
Cost	Free	$150+/mo	Free	Free
Speed	10-30x baseline	Fast (API)	Slow	Slow
XBRL Support	<img src="docs/images/icons/compare-check.svg" width="20"> Full	<img src="docs/images/icons/compare-partial.svg" width="20"> Partial	<img src="docs/images/icons/compare-cross.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">
Financial Statements	<img src="docs/images/icons/compare-check.svg" width="20"> Parsed	<img src="docs/images/icons/compare-check.svg" width="20"> Parsed	<img src="docs/images/icons/compare-partial.svg" width="20"> Basic	<img src="docs/images/icons/compare-cross.svg" width="20"> DIY
LLM-Ready Output	<img src="docs/images/icons/compare-check.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">
Type Hints	<img src="docs/images/icons/compare-check.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">	<img src="docs/images/icons/compare-partial.svg" width="20">	<img src="docs/images/icons/compare-cross.svg" width="20">
Rate Limiting	<img src="docs/images/icons/compare-check.svg" width="20"> Auto	N/A (API)	<img src="docs/images/icons/compare-cross.svg" width="20"> Manual	<img src="docs/images/icons/compare-cross.svg" width="20"> Manual
Open Source	<img src="docs/images/icons/compare-check.svg" width="20"> MIT	<img src="docs/images/icons/compare-cross.svg" width="20"> Proprietary	<img src="docs/images/icons/compare-check.svg" width="20"> Apache	N/A

Use EdgarTools with Claude Code & Claude Desktop

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.

<details> <summary>Setup Instructions</summary>

Option 1: AI Skills (Recommended)

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.

Option 2: MCP Server

Run EdgarTools as an MCP server for Claude Code or Claude Desktop:

pip install "edgartools[ai]"
python -m edgar.ai

Add 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.

</details>

<img src="docs/images/icons/emoji-heart.svg" width="24" height="24"> Support AI Powered Development

I build and maintain EdgarTools solo using AI-assisted development. Your support directly funds the Claude Max subscription that makes this extraordinary velocity possible.

The Virtuous Cycle

<table align="center"> <tr> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-1.svg" width="24" height="24"> You Support Buy Me A Coffee contributions fund Claude Max </td> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-2.svg" width="24" height="24"> AI Acceleration Specialized agents deliver 3-10x faster development </td> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-3.svg" width="24" height="24"> Rapid Delivery Features in days instead of weeks 24 releases / 60 days </td> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-4.svg" width="24" height="24"> You Benefit More features, faster fixes, free forever </td> </tr> </table>

Real Impact: Last 60 Days

<table align="center"> <tr> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-rocket.svg" width="24" height="24"> <h3>24</h3> Releases 1 every 2.5 days </td> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-lightning.svg" width="24" height="24"> <h3>322</h3> Commits 5.4 per day </td> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-target.svg" width="24" height="24"> <h3>3-10x</h3> Velocity vs traditional dev </td> <td align="center" width="25%" valign="top"> <img src="docs/images/icons/emoji-timer.svg" width="24" height="24"> <h3>Days</h3> Not Weeks for major features </td> </tr> </table>

Recent Examples

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:

<img src="docs/images/icons/emoji-check.svg" width="16" height="16"> Claude Max subscription (AI agents that write, test, and document code)
<img src="docs/images/icons/emoji-check.svg" width="16" height="16"> Continued 3-10x development velocity (features in days, not weeks)
<img src="docs/images/icons/emoji-check.svg" width="16" height="16"> Rapid response to SEC format changes and bug reports
<img src="docs/images/icons/emoji-check.svg" width="16" height="16"> New features based on community needs
<img src="docs/images/icons/emoji-check.svg" width="16" height="16"> Free access for everyone, forever (no API keys, no rate limits)

Alternative ways to support:

<img src="docs/images/icons/emoji-star.svg" width="16" height="16"> Star the repo on GitHub
<img src="docs/images/icons/emoji-bug.svg" width="16" height="16"> Report bugs and contribute fixes
<img src="docs/images/icons/emoji-book.svg" width="16" height="16"> Improve documentation
<img src="docs/images/icons/emoji-speech.svg" width="16" height="16"> Answer questions in Discussions
<img src="docs/images/icons/emoji-link.svg" width="16" height="16"> 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.

Documentation & Resources

Get Help & Connect

GitHub Issues - Bug reports and feature requests
Discussions - Questions and community discussions

Contributing

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 <a href="LICENSE">MIT License</a>