The Alpha Stack - 6 financial data providers, one MCP install

Structured data for AI agents.
Not scraped. Not markdown.

GateKey gives your agent schema-stable JSON from SEC filings, earnings calls, market data, and research papers - with provenance, token budgets, and cross-provider joins. One API key. One request shape.

Get 250K free tokensโ†’
$npx @gatekey/mcp-finance(soon)
RequestPOST
// One shape. Every provider.
POST https://api.gatekey.dev/v1/query

{
  "provider": "sec-edgar",
  "endpoint": "/company-facts",
  "params": {
    "ticker": "TSLA",
    "facts": ["Revenue", "NetIncome"],
    "periods": 8
  },
  "controls": {
    "max_tokens": 2000,
    "include_provenance": true
  }
}
Response200
{
  "data": {
    "ticker": "TSLA",
    "facts": [{"metric": "Revenue",
      "value": 25_500_000_000,
      "period": "2024-Q3"}]
  },
  "provenance": {
    "accession": "0001318605-24-015",
    "filed": "2024-10-23",
    "source_url": "https://sec.gov/..."
  },
  "meta": {
    "tokens_used": 847,
    "latency_ms": 312,
    "budget_remaining": 99_153
  }
}
Built by engineers from Scale AI ยท McKinsey
SOC 2 in progress
MIT licensed SDKs (coming soon)
Why GateKey exists

Scrapers give you markdown.
GateKey gives you data.

Web scrapers (Firecrawl, Cloudflare Markdown) convert HTML pages into text. GateKey queries specialized data sources and returns structured, schema-stable JSON with provenance, token counts, and bounded outputs.

โœ— Web scraping / markdown conversion

Scrape a web page - get unstructured text. No schema guarantees. No provenance. Token count varies wildly. Output changes when the page layout changes.

firecrawl.scrape("sec.gov/cgi-bin/browse-edgar?...")
# Tesla Inc - 10-K Annual Report

Filed: October 23, 2024

## PART I

### Item 1. Business

We design, develop, manufacture, sell and
lease high-performance fully electric vehicles
and energy generation and storage systems...

# 16,000+ tokens of raw text
# No structured financials
# No accession number
# Schema changes on next scrape

โœ“ GateKey structured query

Query a data source - get normalized JSON with stable schema, provenance pointers, and exact token budget. Output is consistent across every company, every filing.

gatekey.query("sec-edgar", "/company-facts", ...)
{
  "ticker": "TSLA",
  "facts": [
    {
      "metric": "Revenue",
      "value": 25500000000,
      "period": "2024-Q3",
      "unit": "USD",
      "xbrl_tag": "us-gaap:Revenues"
    }
  }],
  "provenance": {
    "accession": "0001318605-24-015",
    "source_url": "https://sec.gov/...",
    "section": "Financial Statements"
  },
  "meta": { "tokens_used": 847 }
}
Core Architecture

Built for agents, not browsers

Every response from GateKey is engineered for AI consumption - predictable, bounded, traceable.

๐Ÿ“‹

Stable Schemas

Every provider returns the same JSON shape. Tesla revenue looks identical to Apple. Your agent code never breaks when we add providers or sources update their formats.

๐ŸŽฏ

Token Budgets

Set max_tokens per request. GateKey shapes the response to fit your context window - no truncation surprises, no blown budgets. Every response includes exact token count.

๐Ÿ“Ž

Provenance Metadata

Every fact links to its source: accession numbers, filing URLs, section IDs, publication dates. Your agent can cite its work. Auditors can verify it.

โšก

Cross-Provider Joins

One query can pull SEC filings + earnings transcripts + news. GateKey joins across providers so your agent does not need to orchestrate five separate API calls.

The Alpha Stack

The Bloomberg Terminal as an API
for your AI agent

Six financial data providers, structured for agents. One MCP install gives your local Claude or Cursor access to SEC filings, earnings calls, insider trades, market data, and macro indicators.

$npx @gatekey/mcp-finance(coming soon)
FLAGSHIP
Free tier

SEC EDGAR - Parsed

Not raw XBRL. Not adversarial HTML. Normalized financial tables, consistent JSON schemas across 10,000+ companies, section-level extraction from 10-Ks, 10-Qs, and 8-Ks.

Agent use case: Pull Tesla last 8 quarters of revenue with accession numbers and compare to Ford in one query.
FLAGSHIP
Paid tier

Earnings Call Transcripts

Full earnings call transcripts chunked for context windows. Management sentiment extraction, exact CEO/CFO quote attribution, Q&A section parsing. Via Financial Modeling Prep.

Agent use case: Summarize the Q3 earnings call for any ticker and extract the CEO exact quotes about AI investments.
COMING SOON
Paid tier

Insider & Congressional Trades

Real-time SEC Form 4s + congressional stock transactions. Parsed, enriched with committee memberships and disclosure dates. Powered by OpenInsider + Capitol Trades.

Agent use case: Alert me the second a US Senator on the Banking Committee buys a bank stock.
Free tier

FRED - Macro Data

Federal Reserve Economic Data: CPI, employment, housing, GDP, interest rates. Cleaned time-series JSON, ready for agent analysis. No more archaic XML transformation.

Agent use case: Overlay CPI inflation against S&P 500 tech earnings over the last 10 years.
COMING SOON
Paid tier

Real-Time Pricing & Options

Live stock prices, options chains with Greeks, and fundamentals via Polygon.io / Alpha Vantage. Synchronous REST for agents - no WebSocket complexity.

Agent use case: Check live options chain Greeks before executing a paper trade strategy.
Free tier

Financial News

150K+ sources via NewsAPI. Filtered by ticker, sector, or topic. Token-bounded summaries with sentiment scores and source attribution.

Agent use case: Get today top 5 news stories for AAPL with sentiment and source links.
โœ— Without GateKey - 6 APIs, 200+ lines
import requests, feedparser, xml.etree
from alpha_vantage.timeseries import TimeSeries
from fredapi import Fred

# SEC EDGAR - parse XBRL yourself
headers = {"User-Agent": "me@email.com"}
r = requests.get(f"https://efts.sec.gov/...",
  headers=headers)
# handle rate limits (10 rps)
# parse nested XML/HTML
# normalize financial tables manually
# extract accession numbers manually

# Alpha Vantage - different auth, schema
ts = TimeSeries(key='YOUR_KEY')
data, meta = ts.get_quarterly('TSLA')
# 5 calls/min on free tier
# different JSON shape than EDGAR

# FRED - yet another auth + format
fred = Fred(api_key='ANOTHER_KEY')
cpi = fred.get_series('CPIAUCSL')
# returns pandas Series, not JSON

# NewsAPI - yet another key
news = requests.get("https://newsapi.org/v2/...",
  params={"apiKey": "THIRD_KEY", ...})

# Now join all of these together...
# Handle 4 different error formats...
# Count tokens for your context window...
# Hope nothing breaks tomorrow.
โ†’
โœ“ With GateKey - 1 key, 12 lines
from gatekey import GateKey

gk = GateKey(api_key="gk_live_...")

# SEC + Earnings + News in one call
result = gk.query(
  provider="sec-edgar",
  endpoint="/company-facts",
  params={
    "ticker": "TSLA",
    "facts": ["Revenue", "NetIncome"],
    "periods": 8
  },
  controls={
    "max_tokens": 2000,
    "include_provenance": True
  }
)

# Stable schema. Every time.
revenue = result.data.facts[0].value
source  = result.provenance.accession
tokens  = result.meta.tokens_used
budget  = result.meta.budget_remaining

# Same shape for FRED, News, Earnings
macro = gk.query("fred", "/series",
  params={"series_id": "CPIAUCSL"})

# Works as a LangChain tool
tool = gk.as_langchain_tool()
Get started

First API call in under 3 minutes

Sign up, get a key, query any provider. Same request shape for everything.

1

Install

One command for MCP, SDK, or raw REST. Works with Claude, Cursor, LangChain, CrewAI, and any agent framework.

pip install gatekey-ai (soon)npx @gatekey/mcp-finance (soon)
2

Query

One request shape for every provider. POST /v1/query with provider, endpoint, params, and controls. Get structured JSON back.

3

Ship

Token budgets prevent surprises. Provenance metadata enables citations. Scoped keys keep production safe. Agent-ready from day one.

Agent-safe by design

Controls that agents and enterprises expect

As MCP ecosystems grow, security is not optional. GateKey ships with the guardrails production agents need from day one.

๐Ÿ”Scoped API Keys

Restrict keys to specific providers and endpoints. Your SEC-only key cannot query PubMed. Your read key cannot trigger writes.

๐Ÿ•Per-Key Token Budgets

Set daily or monthly hard caps per key. When the budget hits zero, the key stops - no runaway costs from autonomous agents.

๐Ÿ“œAudit Logs

Every query logged with timestamp, provider, token count, and response hash. Export for compliance reviews or SOC 2 evidence.

๐ŸŽ›Response Shaping

max_tokens, include_fields, top_k, dedupe - control exactly what comes back. No context window blowouts.

Coming: Data Marketplace

Agents that pay
for their own data

We are building toward a marketplace where data providers set prices per token, and agents pay autonomously - no enterprise contracts, no manual billing. Powered by x402 agent payment rails.

Providers list content and set royalties. Agents discover, query, and pay - by the token. Developers surface what data they would pay for. The settlement layer between AI agents and the world data.

โšก x402 compatible - machine-to-machine payments
// Coming: agent-initiated data purchases

POST /v1/marketplace/query
{
  "provider": "bloomberg-news",
  "endpoint": "/article",
  "params": {
    "topic": "TSLA earnings"
  },
  "payment": {
    "protocol": "x402",
    "max_spend": "0.05 USDC",
    "wallet": "agent_wallet_0x..."
  }
}

// Response includes payment receipt
{
  "data": { ... },
  "payment_receipt": {
    "tx_hash": "0xabc...",
    "amount": "0.012 USDC",
    "provider_royalty": "0.008",
    "gatekey_fee": "0.004"
  }
}
Pricing

Pay for tokens, not seats

Start free. Upgrade when your agent needs more data. Every plan includes all agent-safe controls.

Free

$0forever
ย 
  • โœ“250,000 tokens / month
  • โœ“5 providers included
  • โœ“60 requests / minute
  • โœ“Scoped keys + budgets
  • โœ“Community support
Get started free
MOST POPULAR

Starter

$29/mo
ย 
  • โœ“5M tokens / month
  • โœ“All providers
  • โœ“300 requests / minute
  • โœ“Audit logs
  • โœ“Email support
Start building

Pro

$99/mo
ย 
  • โœ“50M tokens / month
  • โœ“All providers + premium
  • โœ“1,000 requests / minute
  • โœ“Priority support
  • โœ“Cross-provider joins
Upgrade to Pro

Enterprise

Custom
ย 
  • โœ“Unlimited tokens
  • โœ“10,000+ requests / minute
  • โœ“Dedicated support + SLA
  • โœ“Custom integrations
  • โœ“SSO + RBAC
Talk to us
Who we are

Built by data engineers,
not another AI wrapper

We have built data infrastructure for frontier AI labs and Fortune 500 operations floors. We know what it takes to make data production-grade.

Founding Team

Scale AI ยท McKinsey Alumni

Previously built data infrastructure at Scale AI (serving frontier AI labs, growing from 3 to 50+ enterprise customers) and led operations at McKinsey. We have seen firsthand how painful it is to connect AI agents to real-world data sources - and we are building the infrastructure we wished existed.

Ready?

Give your agent
access to real data.

250,000 free tokens. SEC filings, earnings calls, macro data. First query in under 3 minutes.