Skip to main content
Glama

Mnemom — Trust Ratings for AI Agents

by io.github.mnemom

verify_scan

Read-onlyIdempotent

Verify a website scan scorecard's Ed25519 signature IN-BAND (verify, don't trust). Pass a scan (a scorecard from scan_trust) or a url to re-scan; returns {verified, key_id, canonicalization} checked against the public key at mnemom://iitr/jwks. Zero-auth. Spec + rubric: https://www.isittrustready.ai/rubric and https://docs.mnemom.ai/.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoAlternatively, a domain/URL to re-scan and then verify.
scanNoA scan scorecard previously returned by scan_trust (or iitr's /r/ JSON), passed back verbatim to verify. Same shape as scan_trust's result; the signature is checked against mnemom://iitr/jwks.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
key_idYesThe signing key id (kid) checked.
reasonNoWhy verification failed or could not be evaluated (absent when verified).
verifiedYesTrue iff the signature verifies against the in-band JWKS.
algorithmYesAlways "Ed25519".
scorecardNoThe scorecard verified (present when re-scanned via `url`).
canonicalizationYesThe exact canonicalization used (so the verdict is reproducible).

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / oneOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "url"
+      ]
+    },
+    "required": [
+      "scan"
+    ]
+  },
+  {
+    "not": {
+      "required": [
+        "scan"
+      ]
+    },
+    "required": [
+      "url"
+    ]
+  }
+]
  2. Changed5 schema fields changed
    • addedInput schema / properties / scan / properties / access / properties / categories / description
      Added value: +"Per-category Access scores + checks."
    • addedInput schema / properties / scan / properties / access / properties / grade / description
      Added value: +"Access letter grade (A+…F)."
    • addedInput schema / properties / scan / properties / access / properties / score / description
      Added value: +"0–100 weighted Access/discoverability score (independent of Trust)."
    • addedInput schema / properties / scan / properties / access / properties / version / description
      Added value: +"Access-axis rubric version this sub-score was computed against."
    • addedInput schema / properties / scan / properties / signature / properties / signedAt / description
      Added value: +"When the scorecard was signed."
  3. Changed3 schema fields changed
    • changedInput schema / properties / scan / description
      Previous value: -"A scan scorecard previously returned by scan_trust (or iitr's /r/ JSON) to verify."New value: +"A scan scorecard previously returned by scan_trust (or iitr's /r/ JSON), passed back verbatim to verify. Same shape as scan_trust's result; the signature is checked against mnemom://iitr/jwks."
    • addedInput schema / properties / scan / properties
      Added value: +{
+  "access": {
+    "additionalProperties": true,
+    "description": "The independent Access/discoverability axis (never blended with Trust). Present from the two-axis rubric (0.3.0+).",
+    "properties": {
+      "applicable": {
+        "description": "False when the site declares Access N/A.",
+        "type": "boolean"
+      },
+      "axis": {
+        "description": "Always \"access\".",
+        "type": "string"
+      },
+      "categories": {
+        "items": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "grade": {
+        "type": "string"
+      },
+      "score": {
+        "type": "number"
+      },
+      "version": {
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "cached": {
+    "description": "True when served from the scanner's 24h cache rather than a fresh scan.",
+    "type": "boolean"
+  },
+  "categories": {
+    "description": "Trust-axis categories with per-category scores + checks.",
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "grade": {
+    "description": "Trust letter grade (A+…F).",
+    "type": "string"
+  },
+  "permalink": {
+    "description": "Shareable /r/ permalink (only on /r/ responses; transport field).",
+    "format": "uri",
+    "type": "string"
+  },
+  "rubricVersion": {
+    "description": "Rubric version (e.g. \"0.4.0\").",
+    "type": "string"
+  },
+  "scannedAt": {
+    "description": "When this scorecard was produced. Results are cached up to 24h — pass fresh:true to scan_trust to force a re-scan.",
+    "format": "date-time",
+    "type": "string"
+  },
+  "schema": {
+    "description": "iitr-scan schema version string (e.g. \"iitr-scan/v0.N\").",
+    "type": "string"
+  },
+  "score": {
+    "description": "0–100 weighted overall TRUST score.",
+    "type": "number"
+  },
+  "signature": {
+    "additionalProperties": true,
+    "description": "Ed25519 signature over the canonical result (transport field; stripped before verify).",
+    "properties": {
+      "alg": {
+        "description": "Always \"Ed25519\".",
+        "type": "string"
+      },
+      "publicKeyId": {
+        "description": "16-hex key fingerprint, e.g. 94502b2b7235c986.",
+        "type": "string"
+      },
+      "signedAt": {
+        "format": "date-time",
+        "type": "string"
+      },
+      "value": {
+        "description": "base64 signature.",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "target": {
+    "description": "Normalized host that was scanned.",
+    "type": "string"
+  },
+  "verification": {
+    "additionalProperties": true,
+    "description": "Self-describing in-band verification block {alg, kid, jwks, canonicalization} — how to verify this scorecard's signature. Self-describing, so signed-EXCLUDED (stripped before verify).",
+    "type": "object"
+  }
+}
    • addedInput schema / properties / scan / required
      Added value: +[
+  "schema",
+  "target",
+  "score",
+  "grade",
+  "signature"
+]
  4. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds valuable context beyond annotations: 'Zero-auth', the return shape {verified, key_id, canonicalization}, and that verification uses the public key at mnemom://iitr/jwks. This clarifies auth needs and output without contradicting the safety hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact (two sentences) yet rich with necessary information: purpose, input modes, return shape, key origin, and spec links. Every element earns its place with no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool's complexity (nested scan object, oneOf constraint, output schema), the description covers the essential workflow: how to pass input, what verification is performed, the return value, and where to find detailed specifications. The output schema handles return details, so the description need not repeat them.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents the two parameters, including their types and relationships (oneOf). The description adds a slight clarification that `url` triggers a re-scan, but the schema already states this. No significant additional parameter semantics are provided beyond the structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool verifies a website scan scorecard's Ed25519 signature, distinguishing it from scan_trust (which creates the scorecard) and other verify tools (verify_reputation, verify_agent_binding). The phrase 'IN-BAND (verify, don't trust)' adds specific method and intent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly says to pass either a `scan` from scan_trust or a `url` to re-scan, providing clear input guidance. It does not name specific sibling alternatives or exclusions, but the reference to scan_trust and 'verify, don't trust' implies when to use this tool over blindly accepting a scorecard.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Mnemom — Trust Ratings for AI Agents toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool targets a distinct operation: identity claiming, lookup, reputation retrieval/badge, scanning, verification, alignment/protection management, and feedback. No significant overlap exists.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern using snake_case (e.g., claim_agent, get_reputation, verify_scan). Even complex names like preview_compose_alignment_by_agent adhere to the pattern.

Tool Count4/5

With 16 tools, the set is slightly heavy but still well-scoped for the domain of AI agent trust ratings. Each tool serves a clear purpose, and no tool feels redundant.

Completeness4/5

The surface covers core workflows: agent identity, reputation, alignment/protection, scanning, verification, and feedback. Minor gaps like agent updates or deletion might exist, but the core lifecycle is complete.

Resources