How do I connect an AI agent to drift — mandate enforcement for AI agents?

Use the MCP streamable HTTP endpoint https://drift.rta.lat/mcp.

Catalog › io.github.mrpkk/drift

Is drift — mandate enforcement for AI agents reliable?

Reliable (measured) Yes. Faceabot measured drift — mandate enforcement for AI agents 11 times: 100% of checks succeeded, including the last 11 in a row (last check 2026-10-19 14:00 UTC). It also does the job: its real read-only task worked 11 of 11 times.

Last check: 2026-10-19 14:00 UTC · answered in 10629 ms · remote (no install)

En français : Fiable (mesuré). Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

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

Source: official MCP registry (registry.modelcontextprotocol.io) · version 0.1.0 · publisher website

Connect your agent

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

Or ask Faceabot first: MCP tool check_reliability {"id":"io.github.mrpkk/drift"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked drift_explain to do a small read-only task 11 time(s): 11 returned a real result, the last 11 in a row. Last result: ok in 6780 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-19 14:00 UTC	✅ ok	✅ done	10629 ms
2026-10-18 22:20 UTC	✅ ok	✅ done	5897 ms
2026-10-18 08:10 UTC	✅ ok	✅ done	8841 ms
2026-10-18 00:20 UTC	✅ ok	✅ done	9879 ms
2026-10-17 16:10 UTC	✅ ok	✅ done	7760 ms
2026-10-17 08:05 UTC	✅ ok	✅ done	9400 ms
2026-10-17 00:10 UTC	✅ ok	✅ done	8511 ms
2026-10-16 17:01 UTC	✅ ok	✅ done	10027 ms
2026-10-16 09:55 UTC	✅ ok	✅ done	9037 ms
2026-10-16 03:01 UTC	✅ ok	✅ done	7756 ms
2026-10-15 20:01 UTC	✅ ok	✅ done	9754 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

More from the same publisher

attest — verification for AI agent artifacts Being measured · 0% over 1 checks

Verify an AI agent artifact: schema, emptiness, provenance and mandate authority, Ed25519-signed.

MCP endpoint : https://attest.rta.lat/mcp · website · measurements and details

Publisher of drift — mandate enforcement for AI agents?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/io.github.mrpkk/drift.svg)](https://faceabot.com/tools/io.github.mrpkk/drift)

Data in JSON: /api/catalog?id=io.github.mrpkk/drift · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms