SEC EDGAR Financials MCP. Benchmark metrics and extract GAAP data instantly.
SEC EDGAR Financials provides immediate access to raw XBRL data from U.S. public company filings. Extract key financials like revenue, net income, and total assets for any listed corporation. You can also compare these metrics across entire industries using industry-wide comparison frames.
Give Claude and any AI agent real-world access
Instantly pull the most recent five reported values for crucial figures like revenue, net income, assets, or EPS.
Target and retrieve historical data for any defined US-GAAP financial concept, such as long-term debt or R&D expenses.
Access the complete, comprehensive dataset containing hundreds of XBRL facts across multiple years for deep analysis.
Compare a specific financial metric (like total revenue) across every company within an entire industry sector.
Ask an AI about this
Waiting for input…
What AI agents can do with SEC EDGAR Financials — 4 Tools
These tools let you pull key company financials, query specific GAAP concepts, get the full raw data dump, and compare metrics across entire industry groups.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using SEC EDGAR Financials — Revenue, Income, Assets, EPS & Industry Comparison MCPGet Key Financials
Retrieves the five most recent reported values for core metrics like revenue, net income, and earnings per share.
Get Financial Metric
Fetches historical data for any specific US-GAAP concept, such as Research and...
Get All Company Facts
Provides a complete, raw dataset containing hundreds of XBRL facts across multiple...
Get Industry Comparison
Compares a single financial metric across all companies within an industry frame for...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on each call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with SEC EDGAR Financials — Revenue, Income, Assets, EPS & Industry Comparison, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,200+ others, all in one place
- Add new capabilities to your AI anytime you want
- Connections are secured and governed automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog weekly
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by U.S. Securities and Exchange Commission (SEC). All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS CLOUD
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on each call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Manually building a competitive landscape is brutal.
Think about the old way: You're building a pitch deck, and you need to compare revenue growth across five major industry players. That means downloading five different 10-Q filings. Then, you open Excel, find 'Revenue,' copy the number for Q4 of each company, paste it into your master spreadsheet, and spend an hour just cleaning up dates and ensuring consistent naming conventions.
With this MCP, that whole process vanishes. You simply ask your agent to compare metrics across industries using `get_industry_comparison`. Your agent pulls the standardized numbers directly from the source filings and gives you a clean comparison table instantly. It's pure data output, zero cleanup required.
Get standardized financial data with get_key_financials.
Before this tool, pulling even the basic five-year revenue trend was a tedious copy/paste job. You'd have to navigate through different filing types (10-K vs 10-Q) and find the right line item every single time.
Now, you use `get_key_financials`. It understands which filings hold the most current data for key items like Net Income or EPS. You get a reliable summary view that’s structured by date, saving you hours of manual document review.
What SEC EDGAR Financials MCP does for your AI
When you need hard financial numbers—the kind used by professional analysts—you don't want to sift through endless PDFs. This MCP pulls structured data directly from the SEC EDGAR database, giving your agent a clear view of what big companies report. You can pull key metrics for a specific company using get_key_financials, or you can drill down to isolate one single US-GAAP concept like Research and Development Expense with get_financial_metric.
The real power is comparing whole groups; use the industry comparison tool to benchmark revenue across an entire sector. If you need everything, the full data dump is available via get_all_company_facts. Connecting this MCP through Vinkius gives your AI client a critical edge in market intelligence, allowing it to process and compare metrics that used to take days of manual work.
019d7604-fccc-703a-8b57-ed2473e40907 How to set up SEC EDGAR Financials MCP
The bottom line is, you get clean, standardized financial numbers without ever opening a PDF or running an API call yourself.
You tell your AI client which company and what metrics you need, or if you want to compare entire industries.
The MCP uses the SEC filing structure to pull the correct XBRL data points based on US-GAAP standards.
Your agent receives structured, clean data that includes historical periods and comparison frames, ready for analysis.
Who uses SEC EDGAR Financials MCP
Financial analysts who spend hours cross-referencing GAAP concepts in quarterly filings. Investment bankers needing immediate comparative data for pitch decks. Corporate strategy teams building competitive benchmarks.
They use the MCP to quickly pull get_key_financials for 20 competitors, then run an industry comparison using get_industry_comparison to spot outliers in revenue trends.
When building a comparable company analysis (Comps), they query specific metrics with get_financial_metric—like Cash and Cash Equivalents—to validate valuation assumptions fast.
They use the raw data dump from get_all_company_facts to model long-term historical trends for assets or liabilities, informing major investment decisions.
Benefits of connecting SEC EDGAR Financials MCP
Speed up comps analysis. Instead of manually checking multiple quarters, use get_key_financials to pull the last five reported values for critical metrics like revenue or net income in seconds.
Target difficult concepts easily. Need to know a company's exact long-term debt figure? Use get_financial_metric to query specific US-GAAP concepts, bypassing generalized search results.
Run industry benchmarks instantly. Don’t waste time creating pivot tables; use the comparison tool to see how multiple companies measure up on total assets for CY2024.
Access maximum detail. When quick summaries aren't enough, get_all_company_facts gives you a raw data dump of hundreds of XBRL concepts across years for advanced modeling.
Eliminate ambiguity. The tool is built on official SEC EDGAR filings and US-GAAP standards, ensuring the numbers are reliable and verifiable.
SEC EDGAR Financials MCP use cases
Comparing competitors' growth trajectory
A financial analyst needs to compare how three tech companies handled their R&D spending over the last four years. Instead of downloading and cross-referencing multiple 10-K filings, they use get_financial_metric for 'ResearchAndDevelopmentExpense' across all three firms.
Quick valuation check on a target company
An investment banker needs to verify the latest revenue figures and total assets for a potential acquisition. Using get_key_financials provides an immediate, reliable overview of the five most recent reported values.
Identifying industry sector leaders
A strategy manager wants to know which companies in the retail sector generated the highest revenue last year. They use get_industry_comparison to filter and rank all firms based on a specific metric for CY2024.
Building custom historical models
A data science team needs every financial number available, not just the key metrics. They leverage get_all_company_facts to build comprehensive time-series models using the full XBRL dataset.
SEC EDGAR Financials MCP tradeoffs
What to watch out for, and the recommended way to handle each one.
Treating it like a general database query
Asking the agent, 'What did Apple make last year?' The AI might return vague text or require multiple follow-up prompts to locate the correct filing period and metric.
Always specify the intent. Use get_key_financials first for a summary view, or use get_financial_metric if you need a specific concept like 'NetIncomeLoss' over a defined time frame.
Assuming all data is in one place
Expecting the agent to pull revenue from 10-K filings and debt figures from an annual report using only general chat prompts.
If you need a comparative view, use get_industry_comparison. If you need everything available, start with the raw dump via get_all_company_facts.
Over-relying on surface-level summaries
Accepting only the key metrics and missing crucial historical data points needed for trend analysis.
When deep history matters, use get_all_company_facts to get the full XBRL dataset. This is your source of truth beyond the quick summary.
When to use SEC EDGAR Financials MCP
Use this MCP if your primary need is structured financial data extracted from official U.S. SEC EDGAR filings, particularly when you must compare metrics across multiple companies or time periods based on US-GAAP standards. You should use it when the difference between a rough estimate and verifiable, historical figures matters—think investment research, competitive intelligence, or academic modeling.
Don't use this if you just need general business information (e.g., 'What is Apple's CEO doing today?'). For that, a standard web search works fine. Also, don't use it if your data comes from private company sources; this MCP only handles public filings. If you need to process unstructured text about finances (like news articles), look for an NLP-specific tool instead.
Frequently asked questions about SEC EDGAR Financials MCP
How accurate is the SEC EDGAR Financials—Revenue, Income, Assets, EPS & Industry Comparison MCP? +
The data comes directly from official U.S. Securities and Exchange Commission (SEC) filings using XBRL standards. It's the primary source material for public financial reporting.
Can I use get_industry_comparison to compare metrics across different years? +
Yes, you specify both the metric and the time frame. You can compare Revenue in CY2024 against Revenue in CY2023 using this tool.
What is the difference between get_key_financials and get_all_company_facts? +
Use get_key_financials for a curated, easy-to-read summary of the most recent five periods. Use get_all_company_facts if you need every single historical data point available in the raw XBRL dump.
Does this MCP cover private companies? +
No, this tool is specifically for U.S. public companies that file their reports with the SEC (EDGAR). It cannot access non-public data.
How do I find a specific GAAP concept using get_financial_metric? +
You input the common name of the US-GAAP concept, such as 'LongTermDebt' or 'CommonStockSharesOutstanding,' and the tool returns its historical values for the requested company.