SEC EDGAR financial data. Institutional grade.
One MCP connection gives any AI agent access to 105M SEC facts and 30+ years of financial history — point-in-time accurate, zero survivorship bias.
Get financials for Apple for 2025
Apple (AAPL) — FY2024 Filed: 2024-11-01 (10-K) Revenue $391.0 B ▲ +2.1% YoY Net Income $93.7 B ▲ +11.0% YoY Gross Margin 46.2% EPS (diluted) $6.11 ✓ Point-in-time accurate · No look-ahead bias
$ pip install valuein-sdk
$ echo 'VALUEIN_API_KEY="your_token"' >> .env
from valuein_sdk import ValueinClient, ValueinError
try:
with ValueinClient() as client:
# Build & Run a SQL query
sql = "SELECT COUNT(cik) FROM entity"
result = client.query(sql)
print(result)
# Use a Prebuilt SQL template with params
name = "fundamentals_by_ticker"
tickers = "'AAPL','GOOGL'"
df = client.run_template(name, tickers)
print(df)
except ValueinError as e:
print(f"Catch all errors: {e}")
Works with your existing stack
Your data. Their agents. One protocol.
In 2025, developers queried APIs. In 2026, AI agents query MCP servers. Valuein makes SEC fundamentals a first-class tool for Claude, Cursor, Windsurf, and every autonomous research workflow shipping this year.
One-line connection
Add mcp.valuein.biz/mcp to any MCP-compatible client. Claude, Cursor, Windsurf, custom agents — that's the entire integration.
Token-scoped access
Bearer auth with tiered permissions. Free tier for S&P500. Paid tier for the full universe. One token, enforced at the edge.
Edge-computed queries
DuckDB WASM on Cloudflare Workers. Queries execute at the edge, milliseconds from the data. No server round-trips.
One dataset. Every workflow.
Whether you're an AI agent, a quant, or an analyst building a model — the same institutional-grade data, through the channel built for you.
SEC fundamentals, natively inside your AI agent.
Your AI research assistant is only as good as its data. Give it direct access to 105 million SEC facts — income statements, balance sheets, cash flows — through the Model Context Protocol. No hallucinated numbers. No stale web scrapes. Actual filed data, point-in-time accurate.
- One URL. Every MCP-compatible client connects the same way.
- Queries execute at the Cloudflare edge — <80ms median latency.
- Token-scoped: free tier for S&P500, paid for full 12,000+ universe.
- Ask 'What was Apple's FCF in 2019?' and get the SEC-filed answer.
// Claude asks: "What's Apple's revenue trend?"
// Agent calls:
{
"tool": "get-growth-metrics",
"input": {
"ticker": "AAPL",
"metrics": ["revenue", "net_income"],
"periods": 5
}
}
// Response — actual SEC filings:
{
"cagr_5y": {
"revenue": 0.082, // 8.2% compound
"net_income": 0.091 // 9.1% compound
},
"yoy": {
"revenue": {
"2024": 0.020,
"2023": -0.027,
"2022": 0.078
}
}
}SEC fundamentals. As reported. As they happened.
We don't restate. We don't adjust. Every number is exactly what the company filed with the SEC, timestamped to the moment it became public knowledge. Your backtest sees what the market saw — nothing more, nothing less.
Point-in-Time. Not point-in-hindsight.
Every fact is recorded with its EDGAR acceptance timestamp. Query any date and get exactly what was public knowledge at that moment. No look-ahead bias. No restated surprises. Your 2022 backtest will never accidentally see 2024 amendments.
The dead companies are still here.
Enron. Lehman Brothers. Every delisted, merged, and bankrupt entity that ever filed with the SEC is in our dataset. Your model trains on the full universe — not just the winners that survived.
Don't wait for the quarter.
8-K current reports capture material events as they happen — CEO departures, acquisitions, unexpected write-downs. Most datasets skip these. We parse every one, giving event-driven models a latency advantage over quarterly-only feeds.
Dot-com. Financial crisis. COVID. All of it.
105M+ facts across 12M+ filings dating back to 1993. Deep enough to train ML models across multiple full market cycles and stress-test strategies against every regime shift in modern financial history.
Built for
AI Agents & Copilots
Every MCP-compatible client — Claude, Cursor, Windsurf — gets institutional-grade SEC data with one connection. No SDK. No CSV. Just tool calls.
Quantitative Analysts
Factor models, backtests, and signal research. PIT accuracy eliminates look-ahead bias at the source.
Portfolio Managers
Screen fundamentals, track earnings quality, and stress-test valuations across thousands of companies.
Financial Analysts
Standardized 10-K and 10-Q data in Excel. Your models. Our data. Zero copy-paste errors.
Token-scoped access. Edge-enforced.
Every request is authenticated at the Cloudflare edge. Your token determines data scope and rate limits — checked on every call.
| Tier | Data Scope | Rate Limit | Price |
|---|---|---|---|
| S&P500 | S&P500 · 500+ tickers · 1994–present | 10,000 / day | Free |
| Institutional | Full universe · 12,000+ tickers incl. delisted · 1994–present | Unlimited | $200/mo |
| Custom | Custom · Negotiated universe · redistribution license | Unlimited + SLA | Contact sales |
S&P500 tier — free, no credit card required.
Every AI agent deserves a financial data layer.
Connect your MCP client in 30 seconds. Free tier includes S&P500 companies with full history. No credit card required.