Rein Agent Risk Scale

Name: Rein Agent Risk Scale
Author: reinlayer

Server Details

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

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Last Tested: 2026-10-10 00:30
Transport: Streamable HTTP · MCP 2025-06-18
URL
Repository: reinlayer/rein-examples
GitHub Stars: 0

TDQS

A3.7/5.0

Scored 2026-10-07 19:35 across 3 tools

Disambiguation4/5

explain_grade and get_scale both provide information about grades, creating mild overlap, but their focus differs: one is about requirements for a specific grade, the other is the overall scale reference. self_check is clearly distinct as an interactive assessment tool.

Naming Consistency4/5

All names use snake_case, which is consistent. However, explain_grade and get_scale follow a clear verb_noun pattern, while self_check is a noun compound, which is a minor deviation.

Tool Count5/5

Three tools are well-scoped for this server: one to retrieve the scale, one to explain a grade, and one to self-assess. Each tool serves a distinct purpose with no redundancy.

Completeness4/5

The core interactions (get scale, explain grade, self-check) are covered. However, the description references a verification process and grade publication, yet no tool exists to check verification status or retrieve a verified grade, leaving a minor gap.

Available Tools

3 tools

explain_gradeExplain a grade

Read-onlyIdempotent

Inspect

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

ParametersJSON Schema

Name	Required	Description	Default
`grade`	Yes

get_scaleGet the Rein Agent Risk Scale

Read-onlyIdempotent

Inspect

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

ParametersJSON Schema

Name	Required	Description	Default
No parameters

self_checkSelf-check your Agent Risk Rating

Destructive

Inspect

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.

ParametersJSON Schema

Name	Required	Description	Default
`incidents`	Yes	Q10. Any incidents (bad spend, off-purpose actions, compromise)?
`principal`	Yes	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 platform account claim (which does not count as an accountable principal); or no one.
`monitoring`	Yes	Q9. Is the agent's activity logged, and is anyone looking?
`stop_holder`	Yes	Q5b. Who holds the stop switch?
`stop_switch`	Yes	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.
`agent_handle`	No	Optional public handle (e.g. your Moltbook name). Stored only if publish_opt_in is true. Letters, digits, _ . - only; max 64. Never scored.
`per_week_cap`	Yes	Q3b. Is there a per-week (or per-period) spend cap, and where is it enforced?
`payee_binding`	Yes	Q4. Can the agent pay anyone, or only approved payees / a bound purpose?
`harness_memory`	No	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 sessions); it never moves the letter. Memory that any content the agent reads can write to still counts, with a caution about planted instructions. Not declared scores as none.	not_declared
`publish_opt_in`	No	Set true only if you consent to your grade being published with your handle. Defaults to false; nothing is published without it.
`repayment_path`	Yes	Q2. If you want credit, how would it be repaid? Only matters for the credit add-on.
`eval_session_id`	No	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 on file; a mixed band, or no finished eval at all, holds the grade at B; a weak band holds it at C or below. Nothing in the eval moves a grade up.
`payment_history`	Yes	Q8b. Payment history on any obligations so far.
`human_escalation`	Yes	Q6. Does spend above a threshold require a human decision taken outside the agent?
`months_operating`	Yes	Q8a. How long has this agent been operating?
`controls_evidence`	No	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.	asserted
`per_transaction_cap`	Yes	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?
`base_model_or_harness`	No	Q7 (optional). Do you disclose the base model and harness? Disclosure is scored; which model you run is not.	not_disclosed
`model_or_harness_name`	No	Optional free text, max 80 chars. Stored for research; ignored by the scorer.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

1 tool updateOct 9, 2026

Changedself_check1 field changed

addedInput schema / properties / harness_memory

Added value: +{
+  "default": "not_declared",
+  "description": "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 sessions); it never moves the letter. Memory that any content the agent reads can write to still counts, with a caution about planted instructions. Not declared scores as none.",
+  "enum": [
+    "none",
+    "on_written_by_agent_only",
+    "on_curated_by_operator",
+    "on_writable_by_anything_the_agent_reads",
+    "not_declared"
+  ],
+  "title": "Harness Memory",
+  "type": "string"
+}

2 tool updatesOct 9, 2026

Changedexplain_grade1 field changed

changedInput schema / properties / grade / enum

Previous value: -[
-  "A",
-  "B",
-  "C",
-  "D",
-  "E"
-]New value: +[
+  "A",
+  "B",
+  "C",
+  "D",
+  "NR"
+]

Changedself_check1 field changed

changedInput schema / properties / eval_session_id / description

Previous value: -"Optional. The session_id of a finished behaviour eval (eval mode). Its result is shown beside your indicative grade as evidence. Never scored: it does not change the grade."New value: +"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 on file; a mixed band, or no finished eval at all, holds the grade at B; a weak band holds it at C or below. Nothing in the eval moves a grade up."

3 tool updatesOct 7, 2026
- First observedexplain_grade
- First observedget_scale
- First observedself_check

Related MCP Connectors

YieldSignal A
io.github.Stakemate369
Yield & risk for agents: signal, decision, durability, capacity, sensitivity, exposure, persistence
Finance Blockchain Cryptocurrency
72
PRG Risk Oracle A
io.github.dsrpt1
Market regime, 7-dimension risk vectors and payment hazard grades. Abstains when data is thin.
Finance Payments & Billing
51
AgentIndex — measured reliability for agent services A
io.github.cengit1
Measured uptime, price and payment evidence for 19,021 agent services. Reliability, not quality.
Search Agent Orchestration AI & Machine Learning
221
Texasautoquotes A
com.texasautoquotes
Indicative US auto insurance prices for agents: rating facts only, no PII, consented path to agents.
Finance
81

Related MCP Servers

unphurl-mcp
Web Scraping Security Search
123Ergo
A
license
A
quality
D
maintenance
URL intelligence for AI agents. One URL in, structured security and data quality signals out across 7 dimensions. 13 tools, risk score 0-100 with 23 configurable weights.
Updated 6 months ago (2026-04-23 14:24 UTC)
16
56 npm
1
MIT
zarq-risk-intelligenceofficial
Blockchain Finance Research & Data
zarq-ai
A
license
Not graded
quality
D
maintenance
Real-time crypto risk scoring for AI agents. Trust Score, crash probability, and distance-to-default for 205 tokens. Free, no API key needed.
Updated 7 months ago (2026-03-10 15:44 UTC)
MIT
evidiq-axiom-mcp
Web3 & Decentralized Tech Blockchain
evidiq
F
license
Not graded
quality
B
maintenance
A credit bureau for AI agents that provides proof-backed reputation scoring, attestations, and credit reports. It offers 11 MCP tools for verifying interactions, recommending agents, and managing disputes.
Updated 2 months ago (2026-08-09 03:03 UTC)
1
-
agent-risk-ai
Finance AI & Machine Learning
faanogueira
F
license
Not graded
quality
B
maintenance
Enables AI agents to assess credit default risk, run what-if scenarios, and evaluate portfolios through natural language, backed by an explainable XGBoost model.
Updated 2 months ago (2026-08-24 16:58 UTC)
-