Mnemom — Trust Ratings for AI Agents

get_started

Read-onlyIdempotent

Zero-auth, no-args orientation: who Mnemom is, the surface map, how to authenticate and what it unlocks, and the tools to try right now (scan_trust and the reputation lookups).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`token`	No	Optional Dojo try-me invite token. When supplied and valid, returns the token-gated dojo briefing manifest (the same content as GET /v1/dojo/try-me/resolve); omit for public orientation.

Output Schema

TableJSON Schema

Name	Required	Description
`who`	Yes	One-line positioning.
`verify`	Yes	How to verify signed artifacts in-band (verify, don't trust).
`try_now`	Yes	Zero-auth value tools to call right now.
`doctrine`	Yes
`skill_path`	Yes	The two-step on-ramp to declaring and advertising capabilities as A2A skills in a signed, portable AgentCard.
`value_prop`	Yes	What Mnemom does for an agent.
`surface_map`	Yes	Stable links to the canonical read-only surfaces.
`authenticate`	Yes	How to authenticate and what auth unlocks.
`developer_path`	Yes	The developer hero on-ramp: the npx one-liner plus the intent-named MCP prompt-skills (try-me, onboard_an_agent, become_sovereign). Advertisement only — no functional dependency on those prompts existing yet.
`showcase_agent`	Yes	A real Mnemom-owned agent the try_now reputation reads target, so the loop runs verbatim.
`sovereignty_path`	Yes	The five-step on-ramp to becoming a sovereign, accountable agent, composed from existing tools. Walked end to end by the become_sovereign MCP prompt.
`visibility_model`	Yes	Disambiguates the two axes that share the word 'public': reputation-publication visibility (public by standard) vs identity-record visibility (agent.public), plus the caller-context self-description.
`what_we_keep_private_and_why`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedJul 16, 2026

addedOutput schema / properties / developer_path

Added value: +{
+  "additionalProperties": false,
+  "description": "The developer hero on-ramp: the npx one-liner plus the intent-named MCP prompt-skills (try-me, onboard_an_agent, become_sovereign). Advertisement only — no functional dependency on those prompts existing yet.",
+  "properties": {
+    "narrative": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "npx": {
+      "additionalProperties": false,
+      "properties": {
+        "command": {
+          "type": "string"
+        },
+        "what": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "command",
+        "what"
+      ],
+      "type": "object"
+    },
+    "prompt_skills": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "what": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "name",
+          "what"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "narrative",
+    "npx",
+    "prompt_skills",
+    "note"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / skill_path

Added value: +{
+  "additionalProperties": false,
+  "description": "The two-step on-ramp to declaring and advertising capabilities as A2A skills in a signed, portable AgentCard.",
+  "properties": {
+    "narrative": {
+      "type": "string"
+    },
+    "steps": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "auth": {
+            "enum": [
+              "none",
+              "required"
+            ],
+            "type": "string"
+          },
+          "step": {
+            "type": "integer"
+          },
+          "tool": {
+            "type": "string"
+          },
+          "what": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "step",
+          "tool",
+          "auth",
+          "what"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "narrative",
+    "steps"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "who",
-  "value_prop",
-  "try_now",
-  "authenticate",
-  "sovereignty_path",
-  "surface_map",
-  "showcase_agent",
-  "visibility_model",
-  "what_we_keep_private_and_why",
-  "verify",
-  "doctrine"
-]New value: +[
+  "who",
+  "value_prop",
+  "try_now",
+  "authenticate",
+  "skill_path",
+  "sovereignty_path",
+  "developer_path",
+  "surface_map",
+  "showcase_agent",
+  "visibility_model",
+  "what_we_keep_private_and_why",
+  "verify",
+  "doctrine"
+]

Changed2 schema fields changedJul 2, 2026

addedOutput schema / properties / authenticate / properties / headless

Added value: +{
+  "additionalProperties": false,
+  "description": "The headless/cloud write-auth fallback (MNE-1392): when your host has no local browser and the standard OAuth redirect can't complete, drive the RFC 8628 Device Authorization Grant yourself.",
+  "properties": {
+    "discovery": {
+      "format": "uri",
+      "type": "string"
+    },
+    "grant_type": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "steps": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "use": {
+      "type": "string"
+    },
+    "when": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "when",
+    "use",
+    "grant_type",
+    "discovery",
+    "steps"
+  ],
+  "type": "object"
+}

changedOutput schema / properties / authenticate / required

Previous value: -[
-  "methods",
-  "unlocks",
-  "discovery"
-]New value: +[
+  "methods",
+  "unlocks",
+  "discovery",
+  "headless"
+]

Changed1 schema field changedJun 21, 2026

addedInput schema / properties / token

Added value: +{
+  "description": "Optional Dojo try-me invite token. When supplied and valid, returns the token-gated dojo briefing manifest (the same content as GET /v1/dojo/try-me/resolve); omit for public orientation.",
+  "type": "string"
+}

First observedJun 12, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds value the annotations don't carry: it declares the auth requirement (zero-auth) and enumerates what the orientation unlocks, which is exactly the extra context this dimension rewards. The 'no-args' claim is slightly loose given the optional token parameter, but the schema resolves it.

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?

One front-loaded sentence with no filler; the colon-separated list packs the covered topics and the recommended next tools without redundancy. Nothing can be removed without losing information.

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

Completeness4/5

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

An output schema exists, so return contents need not be described, and the single optional parameter is documented in the schema. The description covers purpose, auth posture, and next steps adequately; only the token-gated variant is left entirely to the schema, which is a minor omission.

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 single optional token parameter is already fully explained in the schema, including the token-gated dojo manifest behavior. The description adds only 'no-args' and does not elaborate on the token path, so the baseline 3 for schema-driven parameter documentation applies.

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

Purpose4/5

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

The description states a specific resource and scope: a zero-auth orientation covering who Mnemom is, the surface map, authentication, and starter tools. It distinguishes itself from siblings by naming scan_trust and the reputation lookups as downstream tools to try. It is not a verb+resource phrasing, but the intent is unambiguous without opening the schema.

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?

'Zero-auth, no-args orientation' plus 'the tools to try right now' gives clear context for when to call this: at the start, before the named sibling tools. It stops short of an explicit 'call this first / don't use it for X' exclusion, so it lands at clear-context-without-exclusions rather than a full routing rule.

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 tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.