# Rein Agent Risk Scale (remote · rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io)

Agent Risk Rating, A–D (NR = not rated): self-declared and unverified; not a credit rating.

- Trust score: 65/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

> **Recent critical change**: Authorization (2026-10-11). See the changelog below before you install this server.

## Components

- remote · `rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io`: 65/100 (this document), [markdown](https://verifymcp.io/servers/reinlayer-rein-agent-risk-scale/rein-scale.md), [page](https://verifymcp.io/servers/reinlayer-rein-agent-risk-scale/rein-scale)

## Channel facts

- Endpoint: `https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.0`

## 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**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (self_check).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 51/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1099 tokens (~366/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the Rein Agent Risk Scale MCP server?

Rein Agent Risk Scale is a hosted endpoint at https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/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 reinlayer-rein-agent-risk-scale 'https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "reinlayer-rein-agent-risk-scale": {
      "url": "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "reinlayer-rein-agent-risk-scale": {
      "type": "http",
      "url": "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.reinlayer-rein-agent-risk-scale]
url = "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "reinlayer-rein-agent-risk-scale": {
      "type": "remote",
      "url": "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add reinlayer-rein-agent-risk-scale --url 'https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  reinlayer-rein-agent-risk-scale:
    url: "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "reinlayer-rein-agent-risk-scale": {
      "Transport": "http",
      "Url": "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add reinlayer-rein-agent-risk-scale -t streamable-http -u 'https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "reinlayer-rein-agent-risk-scale": {
      "type": "http",
      "url": "https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/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.

### 2026-10-17 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-15 (score 64, +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.

### 2026-10-13 (score 63, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 62, +2)

- [security improvement] HSTS header: fail → pass

### 2026-10-11 (score 60, −7)

- [critical regression] Authorization: partial → fail
- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “self_check” rewrote its description, which is the text the model reads
- [security] Tool “get_scale” rewrote its description, which is the text the model reads
- [security] Tool “self_check” is now declared destructive
- [functional regression] Schema quality: 306 → 366
- [functional] Schema quality: excellent → good
- [cosmetic] “self_check” added an optional parameter “harness_memory”
- [cosmetic] “self_check” reworded the description of “eval_session_id”

### 2026-10-09 (score 67)

First indexed and scored.

## MCP tools (3)

### `get_scale` (~29 tokens)

Get the Rein Agent Risk Scale

Returns the A-D Agent Risk Rating scale, what each grade means, the methodology version and the disclaimer.

### `self_check` (~912 tokens)

Self-check your Agent Risk Rating

Score your own agent deployment from structured answers (enums and booleans). Returns an indicative grade (A-D self-declared, or NR when the scale declines to grade), a model-implied expected-loss band beside it, the rated grade (NR until Rein verifies a KYB'd principal), the top 3 reasons and concrete steps that would raise the grade. A sandbox eval band, passed as eval_session_id, affects the grade: A needs a strong band, a mixed band or none holds it at B, a weak band at C or below. Submissions are stored to build a pseudonymised cross-platform record: your answers, your grade, and -- as a label we never score -- the name your software gives itself (an MCP client name and version, or an SDK User-Agent). No IP address is stored. Your handle and that label are published only if you opt in; grades are never published without your agent's opt-in.

Input parameters:

- `agent_handle`: Optional public handle (e.g. your Moltbook name). Stored only if publish_opt_in is true. Letters, digits, _ . - only; max 64. Never scored.
- `base_model_or_harness` (string): Q7 (optional). Do you disclose the base model and harness? Disclosure is scored; which model you run is not.
- `controls_evidence` (string): Q11 (optional). What backs your answers: your own assertion, an independent attestation, or an audit against Rein's factor definitions? Only an audit reaches A.
- `eval_session_id`: Optional. The session_id of a finished behaviour eval (eval mode). Its result is shown beside your indicative grade AND as an input to it (D-262): the band affects the grade. A requires a strong band…
- `harness_memory` (string): Q12 (optional). Does the agent's harness keep memory across sessions, and what writes to it? Memory counts in your favour within your band (it carries mandate changes and payment history across sessi…
- `human_escalation` (string, required): Q6. Does spend above a threshold require a human decision taken outside the agent?
- `incidents` (string, required): Q10. Any incidents (bad spend, off-purpose actions, compromise)?
- `model_or_harness_name`: Optional free text, max 80 chars. Stored for research; ignored by the scorer.
- `monitoring` (string, required): Q9. Is the agent's activity logged, and is anyone looking?
- `months_operating` (string, required): Q8a. How long has this agent been operating?
- `payee_binding` (string, required): Q4. Can the agent pay anyone, or only approved payees / a bound purpose?
- `payment_history` (string, required): Q8b. Payment history on any obligations so far.
- `per_transaction_cap` (string, required): Q3a. Is there a per-transaction spend cap, and is it enforced outside the agent (server-side, by the card issuer or wallet) so the agent cannot raise or bypass it?
- `per_week_cap` (string, required): Q3b. Is there a per-week (or per-period) spend cap, and where is it enforced?
- `principal` (string, required): Q1. Who is accountable for this agent? A registered business that has completed KYB (know-your-business) with a bank or payment provider; a registered business without KYB; a named individual; only a…
- `publish_opt_in` (boolean): Set true only if you consent to your grade being published with your handle. Defaults to false; nothing is published without it.
- `repayment_path` (string, required): Q2. If you want credit, how would it be repaid? Only matters for the credit add-on.
- `stop_holder` (string, required): Q5b. Who holds the stop switch?
- `stop_switch` (string, required): Q5a. Is there a stop/kill switch? Fleet-level means it can halt every deployment sharing this model or harness, not just this one agent.

### `explain_grade` (~36 tokens)

Explain a grade

Explains what a grade on the Rein Agent Risk Scale requires and what moves a deployment up or down.

Input parameters:

- `grade` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/reinlayer-rein-agent-risk-scale/rein-scale#diagnostics

## Score history

- 2026-10-18: 65
- 2026-10-17: 65
- 2026-10-16: 64
- 2026-10-15: 64
- 2026-10-14: 63
- 2026-10-13: 63
- 2026-10-12: 62
- 2026-10-11: 60
- 2026-10-09: 67

## Common questions

### What is the Rein Agent Risk Scale MCP server?

Rein Agent Risk Scale is an MCP server listed in the public MCP registry as io.github.reinlayer/rein-agent-risk-scale. Agent Risk Rating, A–D (NR = not rated): self-declared and unverified; not a credit rating. This page covers its hosted endpoint (https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp).

### Is the Rein Agent Risk Scale MCP server safe to use?

Rein Agent Risk Scale scores 65 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 Rein Agent Risk Scale MCP server expose?

Rein Agent Risk Scale exposes 3 tools: get_scale, self_check, explain_grade. Their descriptions and schemas cost roughly 977 tokens of context every time the server is loaded.

### Does the Rein Agent Risk Scale MCP server require authentication?

No. We connected to Rein Agent Risk Scale without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Rein Agent Risk Scale MCP server still maintained?

Rein Agent Risk Scale 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://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/mcp
- Repository: https://github.com/reinlayer/rein-examples
- Website: https://rein-scale.mangowave-ad191d9c.eastus.azurecontainerapps.io/
- Changelog RSS feed: https://verifymcp.io/servers/reinlayer-rein-agent-risk-scale/rein-scale.xml
- Changelog JSON feed: https://verifymcp.io/servers/reinlayer-rein-agent-risk-scale/rein-scale.json
- HTML version of this page: https://verifymcp.io/servers/reinlayer-rein-agent-risk-scale/rein-scale