cite-finance

cite-finance

Returns verified financial data (SEC EDGAR & FRED) with machine-readable citations. Guaranteed zero hallucinations for AI agents.

Category
访问服务器

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

✅ Zero Hallucination

Pure structured JSON responses - no LLM inference, no made-up numbers.

⚡ Lightning Fast

Sub-300ms p95 latency with 99.9% SLA (Pro tier).

📊 Consistency Scores

Cross-source validation gives you a 0-1 confidence metric on every response.

🔗 SEC Citations

Every data point includes direct links to source filings - perfect for compliance.

🤖 LLM-Ready Format

format=llm option returns prompt-ready text snippets with metadata.

🛡️ Production Grade

Sentry monitoring, Stripe billing, Redis caching, full observability.

Architecture

cite-finance-api/
├── src/
│   ├── api/          # API routes (FastAPI)
│   ├── core/         # Business logic (calculations, metrics)
│   ├── data_sources/ # Plugin-based data source adapters
│   ├── auth/         # API key management
│   ├── billing/      # Stripe integration, usage tracking
│   ├── middleware/   # Rate limiting, auth
│   ├── models/       # Pydantic models
│   └── utils/        # Shared utilities
├── tests/            # Test suite
├── docs/             # API documentation
└── 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:

  • ✅ Structured JSON (no hallucination)
  • ✅ SEC citations with URLs
  • ✅ 96% consistency score
  • ✅ 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

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选