cite-finance
Returns verified financial data (SEC EDGAR & FRED) with machine-readable citations. Guaranteed zero hallucinations for AI agents.
README
Cite-Finance API
Production-grade financial data API with AI-powered synthesis
Overview
Cite-Finance provides SEC EDGAR data, market data, and financial calculations through a clean REST API with built-in AI synthesis capabilities.
What Makes Cite-Finance Different
ā Zero Hallucination
Pure structured JSON responses - no LLM inference, no made-up numbers.
ā” Lightning Fast
Sub-300ms p95 latency with 99.9% SLA (Pro tier).
š Consistency Scores
Cross-source validation gives you a 0-1 confidence metric on every response.
š SEC Citations
Every data point includes direct links to source filings - perfect for compliance.
š¤ LLM-Ready Format
format=llm option returns prompt-ready text snippets with metadata.
š”ļø Production Grade
Sentry monitoring, Stripe billing, Redis caching, full observability.
Architecture
cite-finance-api/
āāā src/
ā āāā api/ # API routes (FastAPI)
ā āāā core/ # Business logic (calculations, metrics)
ā āāā data_sources/ # Plugin-based data source adapters
ā āāā auth/ # API key management
ā āāā billing/ # Stripe integration, usage tracking
ā āāā middleware/ # Rate limiting, auth
ā āāā models/ # Pydantic models
ā āāā utils/ # Shared utilities
āāā tests/ # Test suite
āāā docs/ # API documentation
āāā config/ # Configuration files
Quick Start
Installation
pip install -r requirements.txt
Configuration
cp .env.example .env
# Edit .env with your API keys
Run
uvicorn src.main:app --reload
API Documentation
Once running, visit: http://localhost:8000/docs
Pricing
| Tier | Price | Calls/Month | Key Features |
|---|---|---|---|
| Free | $0 | 50 | Basic metrics, testing |
| Starter | $49 | 2,000 | LLM answers, citations, consistency |
| Professional | $199 | 10,000 | All features, 99.9% SLA |
| Enterprise | $999 | Unlimited | Custom metrics, dedicated support |
Quick Start
1. Get Your API Key
curl -X POST https://api.cite-finance.io/api/v1/auth/register \
-H "Content-Type: application/json" \
-d '{"email": "you@company.com"}'
2. Make Your First Request
curl -H "X-API-Key: your_key" \
"https://api.cite-finance.io/api/v1/answers?ticker=AAPL&metric=revenue_ttm&format=json"
3. Get Structured, Cited Data
{
"ticker": "AAPL",
"metric": "revenue_ttm",
"value": 383285000000,
"unit": "USD",
"period": "TTM",
"as_of": "2024-09-30",
"sources": [
{
"type": "sec_filing",
"filing": "10-K",
"url": "https://www.sec.gov/...",
"excerpt": "Total net sales: $383,285 million"
}
],
"consistency_score": 0.96,
"retrieved_at": "2025-11-24T12:00:00Z"
}
Key Benefits:
- ā Structured JSON (no hallucination)
- ā SEC citations with URLs
- ā 96% consistency score
- ā Sub-300ms response time
Use Cases
- AI Chatbots: Financial Q&A with verified sources
- Trading Bots: High-confidence data for algorithmic trading
- Dashboards: Real-time financial metrics with citations
- Research Tools: Compliance-ready data with SEC links
Documentation
Built For
LLM-first financial applications that need:
- Structured data (no hallucination)
- Verified sources (SEC citations)
- High confidence (consistency scores)
- Production speed (<300ms)
Ready to launch? See DEPLOYMENT_CHECKLIST.md
License
Proprietary - All Rights Reserved
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.