ZARQ Crypto Risk Intelligence — MCP Server

Smithery

Independent crypto risk intelligence via the Model Context Protocol (MCP). Trust Score ratings, Distance-to-Default analysis, structural collapse warnings, and pre-trade safety checks for 198 tokens.

Quick Start

Remote (SSE / Streamable HTTP)

No installation needed — connect directly:

{
  "mcpServers": {
    "zarq-crypto": {
      "url": "https://mcp.zarq.ai/mcp"
    }
  }
}

Local (stdio)

pip install mcp httpx
python zarq_mcp_server.py

Tools (8)

Tool	Description
`crypto_safety_check`	Quick pre-trade safety validation (<100ms)
`crypto_rating`	Full Trust Score with 5-pillar breakdown (A+ to F)
`crypto_dtd`	Distance-to-Default with 7 distress signals
`crypto_signals`	Active Structural Collapse/Stress signals
`crypto_compare`	Head-to-head token risk comparison
`crypto_distress_watch`	All tokens with DtD < 2.0
`crypto_alerts`	Structural collapse/stress warnings
`crypto_ratings_bulk`	Bulk ratings for multiple tokens

Performance

100% death recall — every token collapse detected (out-of-sample)
98% precision — only 1 genuine false positive in OOS validation
198 tokens rated with daily updates
<100ms response time for safety checks

Architecture

Client (Claude, Cursor, etc.)
    ↓ MCP Protocol
ZARQ MCP Server
    ↓ HTTPS
zarq.ai API (free, no key required)

API

Free API at zarq.ai. No API key required during Early Access.

License

MIT

This server cannot be installed

-

security - not tested

A

license - permissive license

-

quality - not tested

How are these scores calculated?

Resources

GitHub Repository

Need Help?

Report Issue

Related Servers

zarq-risk-intelligence