edgar-mcp
Enables querying of SEC EDGAR filings and financial data via natural language, offering tools for company lookup, filing retrieval, XBRL data, and full-text search.
README
SEC EDGAR MCP Server 🏛️
U.S. SEC filings and financial data for Claude Desktop and any MCP-compatible client, powered by SEC EDGAR. Search companies, pull filings (10-K, 10-Q, 8-K, Form 4, ...), read XBRL financials, and full-text search across all filings — all from natural language. No API key required.
npm package:
edgar-mcp· GitHub repo:danishashko/edgar-mcp.
🎯 What You Get
- 🔎 Company lookup by name or ticker → CIK
- 🗂️ Recent filings (any form type) with direct document links
- 📄 Latest filing of a type (newest 10-K / 10-Q / 8-K) in one call
- 💰 Financial highlights (revenue, net income, assets, equity, EPS) from XBRL
- 📈 Concept history — any GAAP line item over time
- 🔬 Full-text search across the last ~10 years of filings
Every tool returns human-readable markdown by default, or structured JSON on request (response_format: "json"). Lightweight (Python standard library + mcp only), no API key, retries on rate limits.
🚀 Quick Start
Add this to your Claude Desktop config and restart Claude:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"edgar": {
"command": "npx",
"args": ["-y", "edgar-mcp"],
"env": {
"SEC_USER_AGENT": "your-app-name your@email.com"
}
}
}
}
The SEC asks every API client to send a descriptive User-Agent with contact info. Set SEC_USER_AGENT to your own name/email (a default is provided so it works out of the box). On first launch the npx wrapper creates an isolated Python environment and installs the dependency (one-time, ~a minute). You need Python 3.10+ and Node.js 16+.
Prefer a global install?
npm install -g edgar-mcp
{
"mcpServers": {
"edgar": {
"command": "edgar-mcp",
"env": { "SEC_USER_AGENT": "your-app-name your@email.com" }
}
}
}
🔧 Available Tools
| Tool | What it returns | Parameters |
|---|---|---|
search_company |
Companies matching a name/ticker, with their CIK | query, limit |
get_recent_filings |
Recent filings (form, dates, link), optional form filter | identifier, form_type, limit |
get_latest_filing |
The newest filing of a given type, with a document link | identifier, form_type |
get_company_facts |
Headline financials (revenue, net income, assets, equity, cash, EPS) | identifier |
get_concept |
One XBRL concept's reported history over time | identifier, concept, limit |
full_text_search |
Filings matching a keyword/phrase across all companies | query, forms, limit |
Every tool also accepts response_format ("markdown", the default, or "json"). identifier accepts a ticker, CIK, or company name.
Common XBRL concepts for get_concept: Revenues / RevenueFromContractWithCustomerExcludingAssessedTax, NetIncomeLoss, Assets, Liabilities, StockholdersEquity, EarningsPerShareDiluted.
💬 Example Prompts
Once the server is connected, just ask Claude:
- "What's Apple's latest 10-K?"
- "Show me Tesla's recent 8-K filings."
- "What are Microsoft's headline financials?"
- "Show me NVIDIA's net income over the last few years."
- "Which companies mention 'quantum computing' in their 10-Ks?"
- "Find the CIK for Berkshire Hathaway."
🐛 Troubleshooting
"SEC EDGAR is rate-limiting requests" EDGAR allows ~10 requests/second. The server retries automatically; wait a moment if it persists.
"Not found"
Use search_company to confirm the exact ticker/CIK first.
"Command not found" / "Python not found"
Ensure Python 3.10+ and Node.js 16+ are installed and on your PATH. On macOS/Linux, try python3.
Tools not showing up in Claude
- Confirm the config file is valid JSON (no trailing commas).
- Fully quit and reopen Claude Desktop.
🛠️ Manual Installation (Alternative)
If you would rather run the Python file directly instead of via npx:
1. Download the server and install the dependency
pip install mcp
(or pip3 on macOS/Linux)
2. Point Claude Desktop at it
{
"mcpServers": {
"edgar": {
"command": "python3",
"args": ["/absolute/path/to/edgar_mcp.py"],
"env": { "SEC_USER_AGENT": "your-app-name your@email.com" }
}
}
}
On Windows use "command": "python" and a path like "C:\\path\\to\\edgar_mcp.py".
3. Restart Claude Desktop.
🔒 Privacy & Rate Limits
- Uses the official SEC EDGAR APIs — public, no key.
- Requests go straight from your machine to the SEC. Nothing is stored or proxied.
- The SEC requires a descriptive
User-Agentwith contact info and limits ~10 requests/second. - Intended for personal, educational, and research use.
📝 Notes
identifieris flexible: ticker (AAPL), CIK (320193), or name (Apple).- Financial data comes from XBRL, first required by the SEC in 2009, so history goes back that far for most filers.
get_company_factsreturns highlights; useget_conceptfor the full series of any one metric.
📋 Changelog
See CHANGELOG.md for the full version history.
📚 Resources
⚖️ Legal Disclaimer
This tool uses the public SEC EDGAR APIs but is not affiliated with or endorsed by the U.S. Securities and Exchange Commission. Use is subject to the SEC's website policies. Data is provided as-is for personal, educational, and research purposes; verify against the original filings before relying on it.
👤 Author
Daniel Shashko
- GitHub: @danishashko
- LinkedIn: daniel-shashko
- npm: danielshashko
📄 License
MIT © Daniel Shashko
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。