# drift — mandate enforcement for AI agents

- Registry name: `io.github.mrpkk/drift` · version 0.1.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.mrpkk%2Fdrift
- Server page: https://mcpstation.net/s/io.github.mrpkk--drift.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://drift.rta.lat/mcp`

## Tools (as reported by the server, not verified)

- `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

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html