oathscore

OathScore

Every API makes promises. OathScore checks the receipts.

The trust layer for AI agents. Two products:

1. /now — A single endpoint returning the current state of the world for trading agents. Exchange status, volatility, events, regime, data health — one call.
2. OathScore Ratings — Independent, continuous verification of data API accuracy, uptime, freshness, and reliability. The credit bureau for data APIs.

For AI Agents

# What's happening right now?
curl https://api.oathscore.dev/now

# Should I trust this data source?
curl https://api.oathscore.dev/score/curistat

# Compare two sources
curl https://api.oathscore.dev/compare?apis=curistat,alphavantage

For MCP-Compatible Agents (Claude Code, Cursor, etc.)

{
  "mcpServers": {
    "oathscore": {
      "command": "python",
      "args": ["-m", "oathscore_mcp"]
    }
  }
}

Requires: pip install httpx mcp[cli] and clone this repo.

MCP Tools

| Tool | Description | |------|-------------| | get_now | Current world state: exchanges, volatility, events, data health | | get_exchanges | Open/close status for 7 exchanges with next transition times | | get_volatility | VIX, VIX9D, VIX3M, VVIX, SKEW, term structure | | get_events | Next event, FOMC/CPI countdowns, week high-impact count | | get_score | OathScore rating for a specific API (0-100 composite + grade) | | compare_apis | Side-by-side comparison of two or more data APIs | | get_alerts | Active degradation alerts for monitored APIs | | check_health | Service health and data freshness |

What OathScore Monitors

For each rated API:

| Metric | Weight | How Measured | |--------|--------|-------------| | Accuracy | 35% | Compare forecasts/claims to actual outcomes daily | | Uptime | 20% | Synthetic monitoring every 60 seconds | | Freshness | 15% | Is "real-time" actually real-time? | | Latency | 15% | P50/P95/P99 from multiple regions | | Schema stability | 5% | Detect breaking changes | | Documentation | 5% | OpenAPI spec, llms.txt, examples | | Trust signals | 5% | Published accuracy data, response signing |

Rated APIs (v1)

| API | Category | Score | Status | |-----|----------|-------|--------| | Curistat | Futures volatility | -- | Monitoring | | Alpha Vantage | Equities/macro | -- | Monitoring | | Polygon.io | Market data | -- | Monitoring | | Finnhub | Multi-asset | -- | Monitoring | | Twelve Data | Market data | -- | Monitoring | | EODHD | Historical data | -- | Monitoring | | Financial Modeling Prep | Fundamentals | -- | Monitoring |

Scores populate after 30 days of monitoring data.

Machine-Readable Discovery

• /llms.txt — Agent-readable product description
• /llms-full.txt — Complete endpoint documentation
• /.well-known/ai-plugin.json — ChatGPT plugin manifest
• /openapi.json — OpenAPI 3.0.3 spec
• /docs — Interactive Swagger UI

Pricing

| Tier | /now Calls | Score Queries | Price | |------|-------------|---------------|-------| | Free | 10/day | 5/day | $0 | | Founding (first 50) | 5,000/day | 2,500/day | $9/mo (lifetime) | | Pro | 10,000/day | 5,000/day | $29/mo | | Enterprise | 100,000/day | 50,000/day | $99/mo | | Pay-per-request (x402) | Unlimited | Unlimited | $0.001-0.005/call |

x402 micropayments: No signup needed. Agents pay per request with USDC stablecoins via the x402 protocol. When rate limited, the API returns 402 Payment Required with payment instructions.

API audits: Independent 7-day quality audit of your API — $299-499. Contact us.

Architecture

[Monitoring Service - Railway $5/mo]
  Every 60s: ping all rated APIs (uptime, latency)
  Every 5m: check data freshness
  Every 1h: record forecast snapshots
  Every 24h: compare forecasts to actuals (accuracy)
  Store: Supabase (free tier)

[/now Endpoint - Cloudflare Workers $0/mo]
  Every 60s: fetch VIX, compute exchange status, read events
  Serve: cached JSON, max-age=30, ETag support

[Scoring Engine - Cloudflare Workers $0/mo]
  Every 5m: recompute composite scores from raw metrics
  Serve: /score, /compare, /alerts endpoints

Integration Examples

CrewAI

from crewai import Agent, Task
from crewai_tools import MCPTool

# Connect to OathScore MCP
oathscore = MCPTool(server_command="python -m oathscore_mcp")

analyst = Agent(
    role="Market Analyst",
    tools=[oathscore],
    goal="Assess current market conditions before trading"
)

task = Task(
    description="Check if markets are open and get current volatility regime",
    agent=analyst
)

LangChain

from langchain_mcp import MCPToolkit

toolkit = MCPToolkit(server_command="python -m oathscore_mcp")
tools = toolkit.get_tools()

# Use in any LangChain agent
from langchain.agents import initialize_agent
agent = initialize_agent(tools, llm, agent="zero-shot-react-description")
agent.run("What's the current VIX level and are US markets open?")

Direct HTTP (any language)

import httpx

# World state in one call
now = httpx.get("https://api.oathscore.dev/now").json()
print(f"VIX: {now['volatility']['vix']}")
print(f"CME: {'OPEN' if now['exchanges']['CME']['is_open'] else 'CLOSED'}")
print(f"Next event: {now['events']['next_event']}")

# API quality check before committing to a data source
score = httpx.get("https://api.oathscore.dev/score/polygon").json()
if score.get("composite_score", 0) < 70:
    print("Warning: data source quality below threshold")

Claude Desktop / Claude Code

Add to your MCP config (~/.claude/mcp.json or Claude Desktop settings):

{
  "mcpServers": {
    "oathscore": {
      "command": "python",
      "args": ["-m", "oathscore_mcp"]
    }
  }
}

Then ask Claude: "What's the current market state?" or "How reliable is Alpha Vantage?"

---

If this is useful, star the repo — it helps others find it.

License

Proprietary. All rights reserved.