Read-only MCP server for SEC EDGAR research and financial analysis.
Retrieve company filings by ticker: 10-K, 10-Q, 8-K, DEF 14A proxies, recent IPOs, and filtered filing lists.
Summarize the latest 8-K and preview latest 10-K/10-Q/8-K filings.
Read or search filing text: page through documents, search inside filings, list documents/exhibits, and check file size before download.
Search EDGAR full text since 2001 by keyword or exact phrase with form/date filters.
Analyze ownership and insiders: Forms 3/4/5 insider transactions, 13D/13G beneficial ownership, and latest 13F fund portfolios.
Access XBRL financial data: company facts, specific concepts, available metrics, and cross-company rankings via XBRL frames.
Run SEC API connectivity checks and a self-test of all tools.
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-ai What does Apple's latest 10-K say about Greater China?"
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.
AI-powered SEC EDGAR integration: 23 tools on the official sec.gov APIs, in one Python file.
š Thousands of downloads on ClawHub and OpenWebUI
10-K, 10-Q, 8-K, 20-F and proxy filings, the full text of any filing read in pages or searched, XBRL company facts and cross-company rankings, Form 4 insider trades, 13D/13G ownership, 13F fund portfolios, IPOs, and full-text search of every filing since 2001.
Use it in | Install | Repo |
Claude, Cursor, VS Code, LangChain, Google ADK, Strands Agents and other MCP clients |
| |
ClawHub skill for OpenClaw š Thousands of downloads |
| |
OpenWebUI tool š Thousands of downloads | ||
Python |
|
Needs uv. No API key.
Claude Code:
claude mcp add sec-ai -e SEC_USER_AGENT="Your Name you@example.com" -- uvx sec-finance-ai@latestVS Code:
code --add-mcp '{"name":"sec-ai","type":"stdio","command":"uvx","args":["sec-finance-ai@latest"],"env":{"SEC_USER_AGENT":"Your Name you@example.com"}}'Claude Desktop, Cursor, Windsurf and other clients, in the client's MCP config file:
{
"mcpServers": {
"sec-ai": {
"command": "uvx",
"args": [
"sec-finance-ai@latest"
],
"env": {
"SEC_USER_AGENT": "Your Name you@example.com"
}
}
}
}@latest picks up new releases when the client starts. Without uv: pip install sec-finance-ai, then use "command": "sec-finance-ai" with no args.
SEC_USER_AGENT is the name and e-mail the SEC asks programs to send. If it is not set, a default is sent.
Listed in the MCP Registry as io.github.lkcair/sec-ai. Every tool is read-only.
Related MCP server: edgar-mcp
The server runs over stdio with uvx sec-finance-ai@latest, so any framework with MCP support can load all its tools.
SEC_USER_AGENT is optional. MCP starts the server with a minimal environment, so pass it as shown; **os.environ keeps PATH, so uvx is found.
LangChain: pip install "langchain[mcp]" langchain-anthropic
import asyncio
import os
from langchain.agents import create_agent
from langchain.mcp import MCPAdapter
async def main():
config = {"mcpServers": {"sec-ai": {
"command": "uvx", "args": ["sec-finance-ai@latest"],
"env": {**os.environ, "SEC_USER_AGENT": "Your Name you@example.com"}, # optional
}}}
async with MCPAdapter(config) as adapter:
tools = await adapter.list_tools()
agent = create_agent("claude-sonnet-5", tools)
result = await agent.ainvoke({"messages": [{"role": "user", "content": "What does Apple's latest 10-K say about Greater China?"}]})
print(result["messages"][-1].content)
asyncio.run(main())Google ADK: pip install "google-adk[mcp]"
import os
from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams
from mcp import StdioServerParameters
root_agent = LlmAgent(
model="gemini-flash-latest",
name="sec_ai",
instruction="Answer with the sec-ai tools.",
tools=[McpToolset(connection_params=StdioConnectionParams(
server_params=StdioServerParameters(
command="uvx", args=["sec-finance-ai@latest"],
env={**os.environ, "SEC_USER_AGENT": "Your Name you@example.com"}, # optional
),
timeout=60,
))],
)Strands Agents: pip install strands-agents
import os
from mcp import stdio_client, StdioServerParameters
from strands import Agent
from strands.tools.mcp import MCPClient
sec_ai = MCPClient(lambda: stdio_client(StdioServerParameters(
command="uvx", args=["sec-finance-ai@latest"],
env={**os.environ, "SEC_USER_AGENT": "Your Name you@example.com"}, # optional
)))
agent = Agent(tools=[sec_ai])
agent("What does Apple's latest 10-K say about Greater China?")What does Apple's latest 10-K say about Greater China?
What are Berkshire Hathaway's top holdings in its latest 13F?
Find every 8-K this year that mentions 'going concern'.
Which companies had the highest revenue in 2024?
Tool | Parameters | Description |
|
| Get SEC filings for a company by ticker symbol |
|
| Latest 10-K with a short preview of its text |
|
| Latest 10-Q with a short preview of its text |
|
| Recent 8-K filings with a short preview of each |
|
| Get and summarize the latest 8-K filing for a company |
|
| Get proxy statements (DEF 14A) for a company |
|
| Get recent IPO activity from EDGAR |
Tool | Parameters | Description |
|
| Exact size of a filing document before downloading it |
|
| Read a filing in 50,000-character pages, search inside it, or get the link when it is over 25 MB |
|
| List every document in a filing (main document, exhibits, XBRL, XML) with sizes and links |
|
| Key financial figures from XBRL, or the full filing text in pages |
Tool | Parameters | Description |
|
| Search the full text of every EDGAR filing since 2001 (words or "exact phrase") |
|
| Search SEC filings by company name or other criteria |
Tool | Parameters | Description |
|
| Get insider trading transactions (Forms 3, 4, 5) for a company |
|
| Get beneficial ownership reports (13D, 13G) for a company |
|
| Get the latest 13F portfolio of an institutional investment manager |
Tool | Parameters | Description |
|
| Get company facts from SEC XBRL data |
|
| Get specific financial concept data for a company |
|
| Discover available financial metrics for a company from SEC XBRL data |
|
| One financial concept across all reporting companies for one period, ranked |
Tool | Parameters | Description |
| Check SEC API status and connectivity | |
| Run comprehensive self-test of all SEC-AI tools |
MIT. All data comes from public SEC EDGAR databases. Not affiliated with the U.S. Securities and Exchange Commission.
Get and summarize the latest 8-K filing for a company.
Args: ticker: Stock ticker symbol
Returns: Dictionary containing 8-K summary with actual content
Inputs: ticker (required). Returns: result
Read or search the text of one SEC filing document. Three modes, chosen automatically:
mode 'text': returns content in pages of max_length characters. If has_more is
true, call again with offset=next_offset to keep reading.
mode 'search': when search is given, returns snippets around each match with its
position (use offset=position to read that part).
mode 'link_only': when the document is larger than the size limit, returns only the link and size so the user can open it. The exact size is checked BEFORE downloading.
Args: filing_url: Filing document URL (https://www.sec.gov/Archives/edgar/data/...) max_length: Characters per page (default 50,000) offset: Character position to start reading from (default 0) search: Optional word or phrase to find inside the filing (case-insensitive)
Returns: Dictionary with mode, filing_url, size_mb, total_characters and content/snippets
Inputs: filing_url (required), offset, search, max_length. Returns: result
Search the full text of every EDGAR filing since 2001 (words or "exact phrase").
Args: query: Words to find, e.g. 'tariffs' or '"going concern"' for an exact phrase form_type: Optional form filter, e.g. '8-K' or '10-K,10-Q' start_date: Optional YYYY-MM-DD (default: one year ago; use '2001-01-01' for all history) end_date: Optional YYYY-MM-DD (default: today) limit: Max results (1-100, default 20)
Returns: Matching filings (newest first) with company, form, date and a link to the matching document
Inputs: query (required), limit, end_date, form_type, +1 more. Returns: result
Get the latest 13F portfolio of an institutional investment manager.
Args: ticker_or_cik: Manager ticker (e.g. 'BRK-B') or CIK (e.g. '1350694' for Bridgewater) limit: Number of top positions to return (default 25)
Returns: Report period, total value, top_issuers (one row per company, share classes combined; use this for "largest holdings") and top_positions (one row per security: CUSIP, share class, put/call)
Inputs: ticker_or_cik (required), limit. Returns: result
Discover available financial metrics for a company from SEC XBRL data.
This function lists ALL available metrics that can be requested via specific_metrics. Useful for AI to find exactly which metrics are available before requesting them.
Args: ticker: Stock ticker symbol (e.g., 'GME', 'AAPL') search_term: Optional search term to filter metrics (e.g., 'EBITDA', 'Revenue', 'Debt')
Returns: Dict containing: - all_metrics: List of ALL available metric names - filtered_metrics: List of metrics matching search_term (if provided) - metric_categories: Organized by category (income, balance_sheet, cash_flow, etc) - total_available: Total number of available metrics - example_ttm_metrics: Example metrics useful for TTM calculations
Inputs: ticker (required), search_term. Returns: result
Get beneficial ownership reports (13D, 13G) for a company.
Args: ticker: Stock ticker symbol limit: Number of reports to return schedule: 'all' (default), '13D' (activist or control intent) or '13G' (passive holder)
Returns: Dictionary containing beneficial ownership information
Inputs: ticker (required), limit, schedule. Returns: result
Get specific financial concept data for a company.
Args: ticker: Stock ticker symbol concept: XBRL concept (e.g., 'Revenues', 'NetIncomeLoss', 'Assets')
Returns: Dictionary containing concept data over time
Inputs: ticker (required), concept (required). Returns: result
Get company facts from SEC XBRL data.
Args: ticker: Stock ticker symbol
Returns: Dictionary containing company facts and financial metrics
Inputs: ticker (required). Returns: result
Get SEC filings for a company by ticker symbol.
Args: ticker: Stock ticker symbol (e.g., 'AAPL', 'TSLA') form_type: SEC form type (e.g., '10-K', '10-Q', '8-K'). Can be a single string or a list of strings. If None, returns all forms. limit: Maximum number of filings to return (default: 10) start_date: Start date for filing search (YYYY-MM-DD format) end_date: End date for filing search (YYYY-MM-DD format)
Returns: Dictionary containing filing information
Inputs: ticker (required), limit, end_date, form_type, +1 more. Returns: result
Get SEC financial data - SMART & EFFICIENT dual-mode approach.
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā ā GENERIC MODE (no specific_metrics parameter) ā ā - Returns 13 essential metrics for any financial analysis ā ā - 5 historical values per metric (sufficient for TTM calc) ā ā - Most token-efficient for general questions ā ā - Includes: Net Income, Revenues, Interest Expense, Taxes, ā ā Operating Income, Gross Profit, Assets, Liabilities, Equity, ā ā Depreciation, Shares Outstanding, Cash, Long-term Debt ā āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā ā SPECIFIC MODE (provide specific_metrics parameter) ā ā - Returns ONLY the requested metrics you specify ā ā - Perfect for targeted analysis (TTM EBITDA, leverage ratios) ā ā - Minimal token usage - only fetch what you need ā ā - Example: ['NetIncomeLoss', 'DepreciationDepletionAndAmortization',ā ā 'InterestExpense', 'IncomeTaxExpenseBenefit'] ā ā - Use get_available_metrics(ticker) to discover all metrics ā āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
WORKFLOW FOR TTM CALCULATIONS:
Call: get_available_metrics(ticker='GME', search_term='Depreciation')
Find needed metrics from results
Call: get_filing_content(ticker='GME', specific_metrics=['NetIncomeLoss', ...])
Calculate TTM from 5 historical values (last 4 quarters + 1 prior)
FILE HANDLING (get_full_content=True):
The exact document size is checked first (EDGAR filing index)
Up to 25MB: first 50,000 characters in full_content; if has_more, continue with download_filing_text(filing_url, offset=next_offset) or search it with search='keyword'
Over 25MB: link only (file_too_large=True), AI told via ai_note
Args: ticker: Stock ticker symbol (e.g., 'GME', 'AAPL') filing_type: Type of filing - '10-Q', '10-K', '8-K', etc. (None = get latest) get_full_content: If True, check and optionally download full filing text specific_metrics: List of specific metric names to fetch. If None, returns 13 essential metrics (generic mode). Example: ['NetIncomeLoss', 'Revenues', 'DepreciationDepletionAndAmortization'] Use get_available_metrics() to discover what's available.
Returns: Dict containing: - ticker, cik, company_name: Company identification - financial_metrics: Dict of requested/essential metrics with 5 historical values each - filing_date, filing_type: Filing metadata - mode: "generic" or "specific" - metrics_returned, values_per_metric: Data shape info - content_mode: 'text' or 'link_only' - full_content, has_more, next_offset: first page of the filing text - file_size_mb, filing_url, ai_note: size, link and what to do next
Inputs: ticker (required), filing_type, get_full_content, specific_metrics. Returns: result
List every document in a filing (main document, exhibits, XBRL, XML) with sizes and links.
Args: filing_url: Any URL inside the filing folder (https://www.sec.gov/Archives/edgar/data/CIK/ACCESSION/...)
Returns: Dictionary with the filing folder and its documents (name, size_bytes, url)
Inputs: filing_url (required). Returns: result
Get the exact size of a filing document BEFORE downloading it.
Use this to decide between reading the text (download_filing_text) and giving the user the link only. Sizes come from the EDGAR filing index.
Args: filing_url: Filing document URL (https://www.sec.gov/Archives/edgar/data/...)
Returns: size_bytes, size_mb, recommendation ('read_text' or 'link_only') and filing_url
Inputs: filing_url (required). Returns: result
Get insider trading transactions (Forms 3, 4, 5) for a company.
Args: ticker: Stock ticker symbol limit: Number of transactions to return
Returns: Dictionary containing insider transaction information
Inputs: ticker (required), limit. Returns: result
Get the latest 10-K filing for a company: filing link plus a SHORT preview of its text.
The preview is only the first 10,000 characters (cover page and first statements). When preview_is_partial is true, follow read_more: download_filing_text(filing_url, offset=...) pages through the rest, download_filing_text(filing_url, search='...') jumps to a section.
Args: ticker: Stock ticker symbol
Returns: Dictionary with the 10-K filing: filing_url, content_preview, preview_characters, total_characters, preview_is_partial and read_more
Inputs: ticker (required). Returns: result
Get the latest 10-Q filing for a company: filing link plus a SHORT preview of its text.
The preview is only the first 10,000 characters (cover page and first statements). When preview_is_partial is true, follow read_more: download_filing_text(filing_url, offset=...) pages through the rest, download_filing_text(filing_url, search='...') jumps to a section.
Args: ticker: Stock ticker symbol
Returns: Dictionary with the 10-Q filing: filing_url, content_preview, preview_characters, total_characters, preview_is_partial and read_more
Inputs: ticker (required). Returns: result
Get proxy statements (DEF 14A) for a company.
Args: ticker: Stock ticker symbol limit: Number of proxy statements to return
Returns: Dictionary containing proxy statement information
Inputs: ticker (required), limit. Returns: result
Get recent 8-K filings for a company with a SHORT preview of each.
Each preview is only the first 5,000 characters. When preview_is_partial is true, follow read_more: download_filing_text(filing_url, offset=...) or download_filing_text(filing_url, search='...').
Args: ticker: Stock ticker symbol limit: Number of recent 8-K filings to return
Returns: Dictionary with 8-K filings: filing_url, content_preview, preview_characters, total_characters, preview_is_partial, read_more and extracted items
Inputs: ticker (required), limit. Returns: result
Get recent IPO activity from EDGAR.
Args: limit: Max companies per list (default 20) days: Look-back window in days (default 30)
Returns: priced: final prospectuses (424B4, filed when an offering is priced) registrations: new S-1 / F-1 registration statements (companies preparing to list)
Inputs: days, limit. Returns: result
Check SEC API status and connectivity.
Returns: Dictionary containing API status information
Inputs: no named parameters. Returns: result
Compare one financial concept across ALL reporting companies for one period.
Args: concept: XBRL tag, e.g. 'Revenues', 'NetIncomeLoss', 'Assets' period: 'CY2024' (annual), 'CY2024Q3' (quarter) or 'CY2024Q4I' (balance-sheet instant) unit: 'USD' (default), 'USD-per-shares', 'shares' taxonomy: 'us-gaap' (default), 'ifrs-full', 'dei' limit: Number of top companies to return (default 20)
Returns: Companies ranked by value for that concept and period
Inputs: period (required), concept (required), unit, limit, +1 more. Returns: result
Run comprehensive self-test of all SEC-AI tools.
Returns: Dictionary containing test results
Inputs: no named parameters. Returns: result
Search SEC filings by company name or other criteria.
Args: query: Search query (company name, ticker, etc.) form_type: SEC form type to filter by start_date: Start date for search (YYYY-MM-DD) end_date: End date for search (YYYY-MM-DD) limit: Maximum number of results
Returns: Dictionary containing search results
Inputs: query (required), limit, end_date, form_type, +1 more. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
Scored across 22 tools
Several tools overlap in retrieving filings and financial data: get_company_filings, search_filings, and full_text_search all return filings; get_filing_content, get_company_facts, get_company_concept, get_available_metrics and get_latest_10k/10q all expose XBRL/financial data. Descriptions provide detail, but an agent could easily misselect among these. Some distinctions are clear (e.g., ownership forms, IPO, admin), but the financial/filing cluster is crowded.
Nearly all tools use snake_case and a get_* prefix for retrievals, with a few verb variations (analyze_8k_filing, download_filing_text, search_filings, full_text_search, run_self_test). The pattern is predictable overall, though full_text_search lacks an explicit verb and search_filings breaks the get_* convention. Minor deviations only.
22 tools for a broad SEC data server is on the heavy side; several financial-data tools could potentially be consolidated (e.g., get_company_facts, get_company_concept, get_available_metrics, get_filing_content). Many tools cover distinct form types and data domains, but the count feels slightly over-scoped rather than lean.
The surface covers filings, financial metrics, ownership (13F, 13D/G, insider, proxy), IPOs, XBRL frames, and admin checks, which is comprehensive for SEC EDGAR data. Minor gaps exist (e.g., no explicit tool for comparing a company's metrics across periods beyond get_company_concept/get_filing_content's 5 values, and no section-level extraction beyond text search). Overall, agents can complete most SEC research workflows.
SEC filings ā 13F, Form 4, 8-K, 13D, IPO and short-interest data ā as 17 agent tools.
Agent-native SEC data, 20 tools: statements assembled, any line item, filings synthesized. No key.
SEC EDGAR data as tools: filing search, full text, XBRL financials, insider trades, 13F, 8-K events.
24-tool hosted SEC EDGAR connector: filings, fundamentals, segments, peers, insiders.
