# nz.agenticrail/gate (remote · mcp.agenticrail.nz)

Deterministic gate for AI agents: ALLOW/DENY a step before it runs, sealed to a verifiable receipt.

- Trust score: 67/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.agenticrail.nz`: 67/100 (this document), [markdown](https://verifymcp.io/servers/nz-agenticrail-gate/mcp.md), [page](https://verifymcp.io/servers/nz-agenticrail-gate/mcp)

## Channel facts

- Endpoint: `https://mcp.agenticrail.nz/`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-08-03.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 2 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 59/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 540 tokens (~270/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http nz-agenticrail-gate https://mcp.agenticrail.nz/
```

### Codex

```toml
[mcp_servers.nz-agenticrail-gate]
url = "https://mcp.agenticrail.nz/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nz-agenticrail-gate": {
      "type": "remote",
      "url": "https://mcp.agenticrail.nz/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add nz-agenticrail-gate --url https://mcp.agenticrail.nz/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  nz-agenticrail-gate:
    url: "https://mcp.agenticrail.nz/"
```

### Other

```json
{
  "mcpServers": {
    "nz-agenticrail-gate": {
      "type": "http",
      "url": "https://mcp.agenticrail.nz/"
    }
  }
}
```

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.

### 2026-08-02 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 66, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 64, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 62, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 61)

First indexed and scored.

## MCP tools (2)

### `evaluate_step` (~358 tokens)

Ask the AgenticRail gate to ALLOW or DENY a single step of an agent sequence BEFORE it runs. The gate is deterministic (same state+request → same verdict) and enforces step order, replay protection (nonce), timestamp freshness, and sealing. A denied step must not be executed. Every decision is sealed into an Ed25519-signed, hash-chained receipt. Returns the decision (ALLOW/DENY/HALT), any reason codes, and receipt metadata. Use the demo key by sending no Authorization header (sequence IDs are auto-prefixed 'demo-'), or send Authorization: Bearer <your-key>.

Input parameters:

- `action` (string): Optional human-readable label for the action.
- `action_type` (string, required): The action class for this step, e.g. CHECK_STATE, SELECT_NEXT_STEP, RECORD_RESULT, PAUSE_CYCLE. Must be permitted for the step.
- `function` (string): Defaults to `step`. The rule step === function always holds.
- `inputs` (object): Optional free-form inputs recorded with the decision.
- `nonce` (string): Optional unique-per-step UUID for replay protection. Generated automatically if omitted.
- `sequence_id` (string, required): Stable identifier for this run of the sequence. Reuse it across every step of the same sequence. Demo callers get a 'demo-' prefix.
- `step` (string, required): The step being attempted, e.g. 'intake' or 'review_and_sign'. Must appear in step_order (for custom sequences) and must equal `function`.
- `step_order` (array): The full ordered list of step names for a CUSTOM sequence. Send it on every call. Omit only if using AgenticRail's built-in MSMD spine.

### `verify_receipt` (~132 tokens)

Fetch the verification report for an AgenticRail sequence and report whether its receipt chain is intact. Demo- sequences need no key; other sequences need Authorization: Bearer <your-key>. Returns the verification_status (VERIFIED_INTACT / CHAIN_BROKEN / …) plus the per-receipt signature, chain-hash, and independent-archive checks. This is the same evidence a third party can verify offline against the published Ed25519 keys — no need to trust AgenticRail.

Input parameters:

- `sequence_id` (string, required): The sequence to verify. Use a 'demo-' sequence for keyless verification.

## Diagnostics

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

## Score history

- 2026-08-03: 67
- 2026-08-02: 67
- 2026-08-01: 66
- 2026-07-31: 66
- 2026-07-30: 64
- 2026-07-29: 63
- 2026-07-28: 63
- 2026-07-27: 62
- 2026-07-26: 61

## Links

- Remote endpoint: https://mcp.agenticrail.nz/
- Website: https://agenticrail.nz/docs/
- Changelog RSS feed: https://verifymcp.io/servers/nz-agenticrail-gate/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/nz-agenticrail-gate/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/nz-agenticrail-gate/mcp