{ "markdown": "\n \"EdgarTools\n\n\n# EdgarTools — Python Library for SEC EDGAR Filings\n\n
\n\n

\n \"PyPI\n \"GitHub\n \"Regression\n \"CodeFactor\"\n \"GitHub\"\n \"Documentation\"\n \"Pepy\n \"Pepy\n \"GitHub\n\n

\n\n**EdgarTools** is a Python library for accessing SEC EDGAR filings as structured data. Parse financial statements, insider trades, fund holdings, proxy statements, and 20+ other filing types with a consistent Python API — in a few lines of code. Free and open source.\n\n![EdgarTools SEC filing data extraction demo](https://raw.githubusercontent.com/dgunning/edgartools/main/docs/images/edgartools-demo.gif)\n\n## Why EdgarTools?\n\nSEC EDGAR has every filing back to 1994, free — and almost none of it is ready to use. EdgarTools turns any filing into a typed Python object, so a 10-K's revenue is one line instead of an afternoon of XBRL parsing.\n\n```python\n# Apple's latest income statement — rendered, standardized, done\nfrom edgar import Company\nCompany(\"AAPL\").get_financials().income_statement()\n```\n\n\n\n \n \n \n\n
\n \"Financial
\n Financial Statements
\n Income, balance sheet, cash flow in one call
\n XBRL-standardized for cross-company comparison\n 		\n \"Every
\n Every Filing Type
\n 13F holdings, Form 4 insiders, 8-K events, funds, proxies
\n Typed objects + pandas DataFrames for 20+ forms\n 		\n \"Built
\n Built for Pipelines & AI
\n Rate-limit aware, smart caching, enterprise mirrors
\n Built-in MCP server + LLM-ready text for RAG\n
\n\n## How It Works\n\nEverything starts with a **`Company`** or a **`Filing`**. Call **`.obj()`** and you get a typed object built for that form — its data ready as pandas DataFrames and clean text.\n\n

\n \"How\n

\n\nThe same typed output that reads cleanly in a notebook drops straight into a pipeline: DataFrames for your warehouse, LLM-ready text and an MCP server for your AI stack, rate-limit and enterprise-mirror aware for scale.\n\n## Quick Start\n\n**1. Install**\n\n```bash\npip install edgartools\n```\n\n**2. Identify yourself to the SEC** — EDGAR requires an email with every request. No key, no signup, no rate-limit tier; set it once:\n\n```python\nfrom edgar import *\nset_identity(\"your.name@example.com\")\n```\n\n**3. Get data** — every filing is now a few lines away:\n\n```python\n# Standardized financial statements, straight from XBRL\nCompany(\"AAPL\").get_financials().income_statement()\n\n# The latest insider Form 4 as a structured object\nCompany(\"AAPL\").get_filings(form=\"4\").latest().obj()\n```\n\n![Apple SEC Form 4 insider transactions parsed into a structured Python object](https://raw.githubusercontent.com/dgunning/edgartools/main/docs/images/quickstart-form4.gif)\n\n**Next:** explore the [Use Cases](#use-cases) below, or dive into the [documentation](https://edgartools.readthedocs.io/) and [Quick Guide](https://edgartools.readthedocs.io/en/latest/quick-guide/).\n\n## Use Cases\n\n### Financial statements from 10-K and 10-Q filings\n\n```python\nfinancials = Company(\"MSFT\").get_financials()\nfinancials.balance_sheet() # all line items\nfinancials.income_statement() # revenue, net income, EPS\n```\n[Financial Statements guide →](https://edgartools.readthedocs.io/en/latest/guides/financial-data/)\n\n### Insider trading from SEC Form 4\n\n```python\nform4 = Company(\"TSLA\").get_filings(form=\"4\").latest().obj()\nform4.to_dataframe() # insider buy/sell transactions\n```\n[Insider Trades guide →](https://edgartools.readthedocs.io/en/latest/insider-filings/)\n\n### 13F institutional holdings & hedge fund portfolios\n\n```python\nthirteenf = get_filings(form=\"13F-HR\").latest().obj()\nthirteenf.holdings # every portfolio position as a DataFrame\n```\n[Institutional Holdings guide →](https://edgartools.readthedocs.io/en/latest/guides/thirteenf-data-object-guide/)\n\n### 8-K current reports & corporate events\n\n```python\neightk = get_filings(form=\"8-K\").latest().obj()\neightk.items # reported event items\n```\n[Current Events guide →](https://edgartools.readthedocs.io/en/latest/guides/eightk-data-object-guide/)\n\n### XBRL financial data across companies\n\n```python\nfacts = Company(\"AAPL\").get_facts()\nfacts.query().by_concept(\"Revenue\").to_dataframe() # revenue history as a DataFrame\n```\n[XBRL Deep Dive →](https://edgartools.readthedocs.io/en/latest/xbrl/)\n\n## Key Features\n\n\n\n\n\n\n
\n\n**Financial data**\n- Income, balance sheet, cash flow — XBRL-standardized for cross-company comparison\n- Individual line items, dimensional data, multi-period comparatives\n- Company Facts API: time-series for any concept across years\n\n**Funds & ownership**\n- 13F holdings, N-PORT, N-MFP, N-CSR/N-CEN fund reports\n- Form 3/4/5 insider transactions; Schedule 13D/G ownership\n- Position tracking over time\n\n\n\n**Filings & text**\n- Typed objects for 20+ forms; complete history since 1994\n- Section extraction (Risk Factors, MD&A), EX-21 subsidiaries, auditor info\n- HTML → clean text + markdown for RAG; full-text search\n- Ticker/CIK lookup, industry & exchange filtering\n\n**Built for production**\n- Configurable rate limiting + enterprise/academic mirrors\n- Smart caching, type hints throughout, 1000+ tests\n- [Enterprise configuration →](docs/configuration.md#enterprise-configuration)\n\n
\n\nEdgarTools 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)**, **S-1 registration statements**, **N-CSR fund reports**, **N-MFP money market data**, **N-PORT fund portfolios**, **Schedule 13D/G ownership**, **Form D offerings**, **Form C crowdfunding**, and **Form 144 restricted stock**. Parse XBRL financial data, extract text sections, and convert filings to pandas DataFrames.\n\n## Comparison with Alternatives\n\nEdgarTools is a **Python library** that talks directly to SEC EDGAR. [sec-api](https://sec-api.io) is the best-known **hosted API** that returns JSON. Both parse filings — the difference is how you work with the data, and what it costs you.\n\n| | EdgarTools | sec-api |\n|---|------------|---------|\n| **Cost** | Free, MIT | $49+/mo |\n| **Data format** | Typed Python objects → DataFrames | JSON you parse yourself |\n| **Where it runs** | In your process — no key, no quotas, no vendor lock-in | Hosted API — key + rate tiers |\n| **Filing coverage** | 20+ typed forms (10-K, 8-K, 13F, N-PORT, proxy…) | 15+ structured endpoints |\n| **AI / MCP** | Built in | |\n| **Open source** | Inspect, fork, self-host | Proprietary |\n\n**Bottom line:** in Python, EdgarTools gives you typed objects, AI-native output, and the full SEC corpus — free, open, and inspectable, with no keys or bills. `pip install edgartools` and you're querying filings in two lines.\n\n## Library or hosted?\n\n**EdgarTools** is the open-source library — SEC-filing primitives you compose in your own code, free and self-run.\n\n[**edgar.tools**](https://edgar.tools) is the hosted platform built on that same open engine: the full SEC corpus as a managed service, so your team gets the data without running the pipeline — and without the black box of a closed API.\n\nReach for the library when you want control in your own stack; reach for **edgar.tools** when you'd rather not operate it yourself.\n\n## AI Integration\n\n### Use EdgarTools with Claude Code & Claude Desktop\n\nEdgarTools includes an MCP server and AI skills for Claude Desktop and Claude Code. Ask questions in natural language and get answers backed by real SEC data.\n\n- *\"Compare Apple and Microsoft's revenue growth rates over the past 3 years\"*\n- *\"Which Tesla executives sold more than $1 million in stock in the past 6 months?\"*\n\n
\nSetup Instructions\n\n### Option 1: AI Skills (Recommended)\n\nInstall the EdgarTools skill for Claude Code or Claude Desktop:\n\n```bash\npip install \"edgartools[ai]\"\npython -c \"from edgar.ai import install_skill; install_skill()\"\n```\n\nThis adds SEC analysis capabilities to Claude, including 3,450+ lines of API documentation, code examples, and form type reference.\n\n### Option 2: MCP Server\n\nRun EdgarTools as an MCP server for any AI client -- Claude Desktop, Cline, or your own containerized deployment.\n\nAdd to Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):\n\n```json\n{\n \"mcpServers\": {\n \"edgartools\": {\n \"command\": \"uvx\",\n \"args\": [\"--from\", \"edgartools[ai]\", \"edgartools-mcp\"],\n \"env\": {\n \"EDGAR_IDENTITY\": \"Your Name your.email@example.com\"\n }\n }\n }\n}\n```\n\nRequires [uv](https://docs.astral.sh/uv/). Alternatively, `pip install \"edgartools[ai]\"` and use `python -m edgar.ai`.\n\nSee [AI Integration Guide](docs/ai-integration.md) for complete documentation.\n\n
\n\n## ❤️ Support This Project\n\nEdgarTools runs in production at hedge funds, fintechs, and research desks — MIT-licensed, no keys, no subscriptions, and maintained by one person.\n\nThe SEC amends filing formats every quarter and ships a new XBRL taxonomy every year. Sponsorship is what keeps 20+ parsers current and funds new extractors as fresh disclosure types appear.\n\n

\n \n \"Sponsor\n \n   \n \n \"Buy\n \n

\n\n

\n Recurring sponsorship + corporate tiers via GitHub · One-time thanks via Buy Me a Coffee\n

\n\n---\n\n### For teams running EdgarTools in production\n\nIf EdgarTools is in your data pipeline, [GitHub Sponsors](https://github.com/sponsors/dgunning) offers corporate tiers from **$250 to $1,500/mo** with:\n\n- Response SLAs (24h–48h first response on critical issues)\n- Quarterly strategy calls and roadmap input\n- Logo placement in this README\n- 7-day early access for internal regression testing\n- Annual invoicing through GitHub — procurement-friendly\n\n→ **[See sponsor tiers](https://github.com/sponsors/dgunning)**\n\n## Community & Support\n\n### Documentation & Resources\n\n- [Documentation](https://edgartools.readthedocs.io/)\n- [Notebooks / Examples](https://edgartools.readthedocs.io/en/latest/notebooks/)\n- [Quick Guide](https://edgartools.readthedocs.io/en/latest/quick-guide/)\n- [EdgarTools Blog](https://www.edgartools.io)\n\n### Get Help & Connect\n\n- [GitHub Issues](https://github.com/dgunning/edgartools/issues) - Bug reports and feature requests\n- [Discussions](https://github.com/dgunning/edgartools/discussions) - Questions and community discussions\n\n### Contributing\n\nContributions welcome:\n\n- **Code**: Fix bugs, add features, improve documentation\n- **Examples**: Share interesting use cases and examples\n- **Feedback**: Report issues or suggest improvements\n- **Spread the Word**: Star the repo, share with colleagues\n\nSee our [Contributing Guide](CONTRIBUTING.md) for details.\n\n### Professional Services\n\nNeed help building production SEC data infrastructure? The creator of EdgarTools offers consulting for teams building financial AI products:\n\n- **SEC Data Sprint** (1–3 days) — Working prototype on your data\n- **Architecture Review** (1–2 weeks) — Pipeline audit with prioritized fixes\n- **Pipeline Build** (2–4 weeks) — Production-ready code, tests, and handoff\n\n[Learn more →](https://www.edgar.tools/consulting)\n\n---\n\n

\nEdgarTools is distributed under the MIT License\n

\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=dgunning/edgartools&type=Timeline)](https://star-history.com/#dgunning/edgartools&Timeline)\n\n\n", "bytes": 14692, "sha": "943bb25c120e0d4965e44f1baa5f3afb82423e5cf9b41155eae5901ca3877f57", "repo_slug": "dgunning/edgartools", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_dgunning_edgartools_35385dbf/readme" }