Skip to main content

​
Architecture overview

Compass is an execution gateway. The agent connects to Compass, not directly to execution tools. Compass evaluates every sensitive call before forwarding it. 
AI agent / MCP client
  ↓
Compass MCP Guard
  ↓
Tool classification
  ↓
Policy + risk checks
  ↓
Simulation / decoding when available
  ↓
Allow, review, or deny
  ↓
Downstream Solana tool / signer
  ↓
Audit log

​
Core components

ComponentRole
MCP guardProxies downstream MCP tools and guards tools/call requests.
Hosted APIAccepts verification requests from custom integrations.
Policy engineApplies limits, allowlists, denylists, and fail-closed defaults.
Risk checksFlags suspicious recipients, risky tools, or unsafe execution conditions.
Audit trailStores decisions with reasons and correlation IDs.

​
Current public surface

  • GET /health — open liveness check.
  • POST /signup — mints an email-scoped API key.
  • POST /v1/verify — returns the live guard verdict.
  • POST /v1/verify/confirm — optional post-execution confirmation path; decoding is still being expanded.

​
Design stance

Compass fails closed for unknown mutating tools. If the system cannot classify an action safely, the answer is deny or review, not silent execution.