# drift — mandate enforcement for AI agents (remote · drift.rta.lat)

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

- Trust score: 18/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `drift.rta.lat`: 18/100 (this document), [markdown](https://verifymcp.io/servers/mrpkk-drift/drift.md), [page](https://verifymcp.io/servers/mrpkk-drift/drift)

## Channel facts

- Endpoint: `https://drift.rta.lat/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 502, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint returned HTTP 502.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the drift — mandate enforcement for AI agents MCP server?

drift — mandate enforcement for AI agents is a hosted endpoint at https://drift.rta.lat/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http mrpkk-drift 'https://drift.rta.lat/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "mrpkk-drift": {
      "url": "https://drift.rta.lat/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "mrpkk-drift": {
      "type": "http",
      "url": "https://drift.rta.lat/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.mrpkk-drift]
url = "https://drift.rta.lat/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mrpkk-drift": {
      "type": "remote",
      "url": "https://drift.rta.lat/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mrpkk-drift --url 'https://drift.rta.lat/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  mrpkk-drift:
    url: "https://drift.rta.lat/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "mrpkk-drift": {
      "Transport": "http",
      "Url": "https://drift.rta.lat/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add mrpkk-drift -t streamable-http -u 'https://drift.rta.lat/mcp'
```

### Other

```json
{
  "mcpServers": {
    "mrpkk-drift": {
      "type": "http",
      "url": "https://drift.rta.lat/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 18, −48)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] HTTPS: fail → unverified
- [security regression] Stability: 0.07 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [functional regression] Capabilities: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-16 (score 66, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-15 (score 65)

First indexed and scored.

## MCP tools (3)

### `drift_check` (~252 tokens)

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 spends money, moves a credential or changes state on someone else's behalf.

Do NOT use to: verify mandate signatures (AP2 does that, and this server runs after signature verification), execute the action (it only decides), or certify that an intent is truthful — "intent" arrives from the agent and is untrusted input. An agent that lies within its limits still leaves a ledger entry; proving what really happened is attest's job, not this one's.

Amounts are integer minor units (cents), never floats. Window bounds are inclusive. Fully idempotent: the same inputs always give the same verdict and the mandate is never mutated.

Input parameters:

- `action` (object, required): The action being proposed.
- `mandate` (object, required): The signed authority being enforced. Treat as read-only input.

### `drift_session` (~164 tokens)

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 as evidence of what actually happened. It reports what was PROPOSED against a mandate you supply.

Read-only. Idempotent for a fixed action list. Amounts in integer minor units, as in drift_check.

Input parameters:

- `actions` (array, required): Proposed actions in order. Order affects the fingerprint.
- `mandate` (object, required): Same shape as in drift_check.

### `drift_explain` (~116 tokens)

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 will fire, only the order they are tried in.

Constant output, fully idempotent, opens no files, contacts no host.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/mrpkk-drift/drift#diagnostics

## Score history

- 2026-10-18: 18
- 2026-10-17: 66
- 2026-10-16: 66
- 2026-10-15: 65

## Common questions

### What is the drift — mandate enforcement for AI agents MCP server?

drift — mandate enforcement for AI agents is an MCP server listed in the public MCP registry as io.github.mrpkk/drift. Block an action a signed mandate does not permit: amount, payee, audience, currency, window, intent. This page covers its hosted endpoint (https://drift.rta.lat/mcp).

### Is the drift — mandate enforcement for AI agents MCP server safe to use?

drift — mandate enforcement for AI agents scores 18 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the drift — mandate enforcement for AI agents MCP server expose?

drift — mandate enforcement for AI agents exposes 3 tools: drift_check, drift_session, drift_explain. Their descriptions and schemas cost roughly 532 tokens of context every time the server is loaded.

### Does the drift — mandate enforcement for AI agents MCP server require authentication?

Its publisher declares no required credentials for drift — mandate enforcement for AI agents. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the drift — mandate enforcement for AI agents MCP server still maintained?

drift — mandate enforcement for AI agents is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://drift.rta.lat/mcp
- Repository: https://github.com/mrpkk/drift
- Website: https://drift.rta.lat/
- Changelog RSS feed: https://verifymcp.io/servers/mrpkk-drift/drift.xml
- Changelog JSON feed: https://verifymcp.io/servers/mrpkk-drift/drift.json
- HTML version of this page: https://verifymcp.io/servers/mrpkk-drift/drift