io.github.mrpkk/drift · v0.1.0 · agents-and-memory
drift — mandate enforcement for AI agents is healthy: it completed an MCP handshake in 2492 ms and exposes 3 tools.
Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.
Endpoint: https://drift.rta.lat/mcp (streamable-http)
Repository · Website · JSON · Add to my inventory
| Users (last 30 days) | 0 |
| Handshake | Healthy |
| Auth needed | None |
| Tool count | 3 |
| Latency | 2492 ms |
| Last checked (UTC) | 2026-10-15T20:50:09.153Z |
| Checked (UTC) | Status | Latency | Error |
|---|---|---|---|
| 2026-10-15T20:50:09.153Z | Healthy | 2492 |
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, audienc |
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 w |