All servers · AI models & agents

drift — mandate enforcement for AI agents

io.github.mrpkk/drift · v0.1.0

Measured by MCP Station

Description written by the publisher, not verified

Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.

Connect

claude mcp add --transport http drift https://drift.rta.lat/mcp

{
  "mcpServers": {
    "drift": {
      "url": "https://drift.rta.lat/mcp"
    }
  }
}

Tools as reported by the server

• drift_check
  Check ONE proposed action against a signed agent mandate BEFORE it happens. Returns {"verdict": "ALLOW"|"DENY", "rule": <name>} plus a report with a ledger fingerprint. Six rules run in a fixed order, so a refusal names the most important reason rather than an incidental one: amount, payee, audience
• drift_session
  Check a SEQUENCE of proposed actions against one mandate. Returns {submitted, allowed, denied, breach_by_rule, fingerprint}. Use for a whole plan or batch, not a single action — use drift_check for that. The fingerprint is the point: rewriting or reordering any earlier decision changes the hash, so
• drift_explain
  Return the six enforcement rules in the exact order they are applied, each with a plain-language reason it exists. Takes no mandate and no action. Use when a refusal did not make sense, or before explaining a denial to someone whose mandate was rejected. A refusal you cannot explain is one nobody wi

Repository · Website · JSON · Text for agents · Registry updated 2026-10-15