A
licenseA
qualityC
maintenanceMCP server providing read-only access to SEC EDGAR filings, allowing LLMs to look up companies, search filings, and retrieve securities offering data.
3
80 PyPI
2
MIT
SEC EDGAR MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@SEC EDGAR MCP Get Apple's latest 10-K filing"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
SEC EDGAR MCP
MCP server for accessing SEC EDGAR filings. Connects AI assistants to company filings, financial statements, and insider trading data with exact numeric precision.
Built on sec-edgar-toolkit.
https://github.com/user-attachments/assets/d310eb42-b3ca-467d-92f7-7d132e6274fe
NOTE
This project is not affiliated with or endorsed by the U.S. Securities and Exchange Commission. EDGAR and SEC are trademarks of the SEC.
Quick Start
{
"mcpServers": {
"sec-edgar-mcp": {
"command": "docker",
"args": [
"run", "-i", "--rm",
"-e", "SEC_EDGAR_USER_AGENT=Your Name (your@email.com)",
"stefanoamorelli/sec-edgar-mcp:latest"
]
}
}
}The -i flag is required for MCP's JSON-RPC communication.
For other installation methods (pip, uv), see the documentation.
Related MCP server: sec-edgar-mcp
Tools
Category | Tools |
Company | CIK lookup, company info, company facts |
Filings | 10-K, 10-Q, 8-K retrieval, section extraction |
Financials | Balance sheet, income statement, cash flow (XBRL-parsed) |
Insider Trading | Form 3/4/5 transactions |
All responses include SEC filing URLs for verification.
HTTP Transport
For platforms like Dify, use streamable HTTP instead of stdio:
python -m sec_edgar_mcp.server --transport streamable-http --port 9870No authentication is included. Use only on private networks.
Evaluations
Promptfoo-based test suite. See evals/ for details.
cd evals && npm install && npm run evalDocumentation
Full docs: sec-edgar-mcp.amorelli.tech
Contributors
Citation
If you use this software in research, please cite it:
@software{amorelli_sec_edgar_mcp_2025,
title = {{SEC EDGAR MCP (Model Context Protocol) Server}},
author = {Amorelli, Stefano},
version = {1.0.6},
year = {2025},
month = {9},
url = {https://doi.org/10.5281/zenodo.17123166},
doi = {10.5281/zenodo.17123166}
}See CITATION.cff for additional formats.
License
AGPL-3.0. For commercial licensing: stefano@amorelli.tech
Available Tools
21 toolsanalyze_8kA
Analyze an 8-K current report for material events.
Args: identifier: Company ticker symbol or CIK number accession_number: The 8-K filing accession number
Returns: Analysis of reported items: Material agreements Results of operations (earnings) Officer/director changes Regulation FD disclosures Other material events
Inputs: identifier (required), accession_number (required).
analyze_form4_transactionsD
Inputs: identifier (required), days, limit.
analyze_insider_sentimentA
Analyze insider trading patterns and frequency.
Args: identifier: Company ticker symbol or CIK number months: Number of months to analyze (default: 6)
Returns: Filing frequency analysis (high/moderate/low) and recent activity summary.
This provides frequency analysis only. For buy/sell sentiment, use analyze_form4_transactions to examine actual transaction details.
Inputs: identifier (required), months.
compare_periodsD
Inputs: metric (required), end_year (required), identifier (required), start_year (required).
discover_company_metricsA
Discover what financial metrics are available for a company.
Use this tool to find available XBRL concepts before using get_key_metrics.
Args: identifier: Company ticker symbol or CIK number search_term: Filter metrics by name (optional)
Returns: List of available XBRL concepts with data counts.
Inputs: identifier (required), search_term.
discover_xbrl_conceptsB
Discover all XBRL concepts available in a filing.
Use this to explore available data before extracting specific concepts.
Args: identifier: Company ticker symbol or CIK number accession_number: Specific filing accession number (optional) form_type: Form type if no accession number provided (default: "10-K") namespace_filter: Filter by namespace (e.g., "us-gaap")
Returns: All discovered concepts, namespaces, and sample values.
Inputs: identifier (required), form_type, accession_number, namespace_filter.
get_cik_by_tickerA
Convert a stock ticker symbol to its SEC CIK (Central Index Key).
Args: ticker: Stock ticker symbol (e.g., "AAPL", "NVDA", "MSFT")
Returns: CIK number for use with other SEC EDGAR tools.
Inputs: ticker (required).
get_company_factsD
Inputs: identifier (required).
get_company_infoA
Retrieve company information from SEC records.
Args: identifier: Company ticker symbol or CIK number
Returns: Company details including name, CIK, SIC code, exchange, and fiscal year end.
Inputs: identifier (required).
get_filing_contentA
Get the content of a specific SEC filing with paging support.
Args: identifier: Company ticker symbol or CIK number accession_number: The accession number of the filing offset: Character offset into the filing content (default: 0) max_chars: Maximum number of characters to return (default: 50000)
Returns: Dictionary containing filing content page and pagination metadata
Inputs: identifier (required), accession_number (required), offset, max_chars.
get_filing_sectionsA
Extract specific sections from 10-K or 10-Q filings.
Args: identifier: Company ticker symbol or CIK number accession_number: Filing accession number form_type: Form type ("10-K" or "10-Q")
Returns: Extracted sections including business description, risk factors, and MD&A.
Inputs: form_type (required), identifier (required), accession_number (required).
get_financialsD
Inputs: identifier (required), statement_type.
get_form4_detailsD
Inputs: identifier (required), accession_number (required).
get_insider_summaryA
Get a summary of insider trading activity.
Args: identifier: Company ticker symbol or CIK number days: Number of days to analyze (default: 180)
Returns: Summary with filing counts by form type, unique insiders, and recent activity.
Inputs: identifier (required), days.
get_insider_transactionsD
Inputs: identifier (required), days, limit, form_types.
get_key_metricsD
Inputs: identifier (required), metrics.
get_recent_filingsA
Get recent SEC filings for a company or across all filers.
Args: identifier: Company ticker/CIK (optional, omit for all recent filings) form_type: Filter by form type (e.g., "10-K", "10-Q", "8-K", "4") days: Number of days to look back (default: 30) limit: Maximum filings to return (default: 50)
Returns: List of filings with dates, form types, accession numbers, and SEC URLs.
Inputs: days, limit, form_type, identifier.
get_recommended_toolsA
Get recommended tools for analyzing a specific SEC form type.
Args: form_type: SEC form type (e.g., "10-K", "8-K", "4", "DEF 14A")
Returns: Recommended tools and usage tips for the form type.
Inputs: form_type (required).
get_segment_dataD
Inputs: identifier (required), segment_type.
get_xbrl_conceptsD
Inputs: identifier (required), concepts, form_type, accession_number.
search_companiesB
Search for companies by name in SEC records.
Args: query: Company name search query limit: Maximum results to return (default: 10)
Returns: List of matching companies with CIK and ticker information.
Inputs: query (required), limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
C2.5/5.0
Scored across 21 tools
Disambiguation2/5
Multiple tools have overlapping purposes, especially in the insider trading (5 tools) and financial metrics (7 tools) areas. While each has distinct nuances, the boundaries are unclear and could lead to agent confusion.
Naming Consistency4/5
Most tools follow a verb_noun pattern (analyze_, discover_, get_, search_), but there are minor inconsistencies such as 'get_cik_by_ticker' with a preposition and 'compare_periods' without a clear prefix. Overall readable and predictable.
Tool Count4/5
21 tools is slightly above the typical well-scoped range (3-15), but given the breadth of SEC EDGAR data (filings, financials, insider trading), the count is still reasonable and each tool serves a specific need.
Completeness4/5
The tool set covers major areas: company lookup, filings, financial metrics, and insider trading. Minor gaps exist, such as no historical filing list beyond a few days and no full-text search across filings, but core workflows are supported.
Maintenance
ActivitySlowing
ResponsivenessLimited data
Related MCP Connectors
Read, search, and compare SEC EDGAR filings, pull tables, and run AI analysis from any MCP client.
SEC EDGAR financials, insider trading, and economic data for AI agents. US GAAP + IFRS.
Real SEC, 13F, insider, congress & macro data your AI agent can cite. Hosted MCP, 24 tools.
Your agent needs company financials it can compute on — statements, ratios, earnings, estimates, filings and insider activity as structured data, not a PDF. **What you can ask for** • "Give me 8 quarters of income statement, balance sheet and cash flow for this ticker." • "What do analysts estimate for next quarter, and how did the last four surprise?" • "Find this exact line item across every filing." • "Who bought or sold as an insider in the last 90 days?" • "Screen for profitable companies under this valuation with growing revenue." **How to use it** Point any MCP client at https://mcp.aisa.one/marketpulse/mcp and sign in with OAuth — there is no key to create or paste. 21 tools: prices and snapshots, income statements, balance sheets, cash-flow statements, financial metrics and snapshots, earnings, analyst estimates, company facts, filings and filing items, line-item search, a screener, insider trades, macro interest rates, news, plus EDINET documents and filing digests for Japanese issuers. **Why this rather than the source** Statements as fields you can compute on, and a screener in the same place. **It is also a door to the rest** The same login reaches 26 sources and 580+ operations. Read the fundamentals here, then ask the same agent what social is saying about the ticker — without adding a second server. **What it costs** Finding and inspecting an operation is free. Running one is billed per call at API prices, with no seat and no monthly minimum, and every call takes max_price_usd so an agent cannot overspend by accident. **Where else it reaches** https://mcp.aisa.one/finance/mcp for equities, crypto and prediction markets in one place.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceHosted MCP server that gives AI agents real-time access to SEC EDGAR filings search, 10-K/8-K reading, XBRL financial facts, and insider-trade (Form 4) alerts.12 npm1MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for SEC EDGAR that provides real-time access to filings, financial statements, and full-text search across all EDGAR documents.Apache 2.0
- AlicenseAqualityBmaintenanceAn MCP server that enables models to access SEC EDGAR filings, filing text, and XBRL financial facts with caching, rate limiting, and iXBRL stripping.8MIT