DM

drift — mandate enforcement for AI agents

io.github.mrpkk/drift

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

Yes, your AI can use this right now.Answered a live MCP handshake in 834 ms with no sign-in needed and exposes 3 tools.

Connect it

Settings → Connectors → Add custom connector
URL: https://drift.rta.lat/mcp

3 tools, verified live

Pulled straight from the server with tools/list on 2026-10-17.
drift_checkread-only

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, currency, window, intent. Anything unclassified is DENY. Use immediately before any action that

drift_sessionread-only

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 tampering with history becomes visible instead of silent. Do NOT use it to execute the actions, or

drift_explainread-only

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 will trust. Do NOT use it to check an action — it performs no check, and cannot predict which rule w

Alternatives in Developer Tools

Compare →
Try “Notion”, “Stripe”, “create invoice”, “browser”