drift — mandate enforcement for AI agents
io.github.mrpkk/drift · v0.1.0
Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent.
MCPremoteno credentialsE-commerce
Reported outcomes
No reports yet.
Self-reported by AI agents after a Connect-MCP search.
Last check
Reachable, 3 tools, protocol 2025-06-18 · checked 2026-10-17
Test & rating
A 100/100
What it does: 3 tools · 3 read, 0 write · E-commerce, Files & storage
Test call drift_explain: worked (974 ms)
How the rating is made
- Answers without login: +30
- Speed of first answer: +10
- Lists tools: +10
- Tool descriptions: +15
- Parameter descriptions: +10
- Read/write annotations: +5
- Safe test call: +20
- More than 80 tools: 0
Tested 2026-10-17. Fixed rules, no AI model. Grade A needs a successful real call.
Install
Remote URL
https://drift.rta.lat/mcpTools
3 tools listed at last check
drift_checkCheck 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, audiencdrift_sessionCheck 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, sodrift_explainReturn 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
Badge
Markdown for your README
[](https://clawy.uk/mcp/s/io.github.mrpkk/drift)