Skip to main content
Glama

AINumbers Fintech Intelligence Suite

by co.ainumbers
OverviewDiscussionsAdmin

Agent Identity & Authorization Attestation Checker

check_agent_attestation
Read-onlyIdempotent

Agent Identity & Authorization Attestation Checker: OpenChainGraph compute node (compliance_mandate). Regulatory deadline: 2027-12 (EU AI Act Annex III high-risk obligations (Digital Omnibus, Parliament final approval June 2026) push agent KYA toward compliance requirement from 2 December 2027; KYA-OS donated to DIF March 2026). Deterministic OpenChainGraph compute node. By default (compute:"auto") inputs are computed server-side on Cloudflare Workers for gpu:false nodes with a registered kernel; compute:"browser" forces client-side execution and returns a browser delegation URL instead. gpu:true nodes always delegate to the browser. Inputs are processed transiently to compute the response and are not stored, logged, or retained. Use synthetic or anonymised inputs only. Exports an AP2 artifact with execution_hash for chain provenance. Consumes upstream artifacts from: art-01-ap2-mandate-chain-validator, art-02-agent-spend-policy-simulator, art-13-eudi-wallet-credential-readiness-checker. Output feeds: art-02-agent-spend-policy-simulator, art-32-a2a-agent-card-trust-chain-validator, ptg-01-ap2-prompt-template-generator. Open at: https://ainumbers.co/chaingraph/art-04-agent-identity-attestation-checker.html FV-status (published/proven/still-trusted for this spec): /fv-status/8498d0819c941fdb731f9e10f5d93ee929026919cb111a42149821b48b5ac180.json — a snapshot, not a subscription; this receipt verifies offline regardless of whether that file is ever fetched. Output schema: call describe_tool("check_agent_attestation").

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
computeNoCompute mode (v0.4 Compute Binding). "auto" (default) = server for gpu:false nodes with registered kernels; "server" = force server-side; "browser" = always return browser delegation URL. gpu:true nodes always delegate.
parent_hashesNoexecution_hash values from upstream ChainGraph AP2 artifacts to chain from (sets chain.parent_hashes in the export).
parent_tool_idsNotool_id values matching parent_hashes, in the same order.
policy_parametersNoInput parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is "auto" or "server". See the tool's manifest for field names.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "checks": {
-      "items": {
-        "properties": {
-          "code": {
-            "type": "string"
-          },
-          "status": {
-            "type": "string"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "fail": {
-      "type": "integer"
-    },
-    "overall_status": {
-      "type": "string"
-    },
-    "pass": {
-      "type": "integer"
-    },
-    "root_agent_id": {
-      "type": "string"
-    },
-    "scopes": {
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    "warn": {
-      "type": "integer"
-    }
-  },
-  "type": "object"
-}New value: +null
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "checks": {
+      "items": {
+        "properties": {
+          "code": {
+            "type": "string"
+          },
+          "status": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "fail": {
+      "type": "integer"
+    },
+    "overall_status": {
+      "type": "string"
+    },
+    "pass": {
+      "type": "integer"
+    },
+    "root_agent_id": {
+      "type": "string"
+    },
+    "scopes": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "warn": {
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}
  3. Changed3 schema fields changed
    • addedInput schema / properties / compute
      Added value: +{
+  "description": "Compute mode (v0.4 Compute Binding). \"auto\" (default) = server for gpu:false nodes with registered kernels; \"server\" = force server-side; \"browser\" = always return browser delegation URL. gpu:true nodes always delegate.",
+  "enum": [
+    "auto",
+    "server",
+    "browser"
+  ],
+  "type": "string"
+}
    • removedInput schema / properties / inputs
      Removed value: -{
-  "additionalProperties": {},
-  "description": "Simulation parameters for this tool's input fields. See the tool's embedded manifest for field names.",
-  "propertyNames": {
-    "type": "string"
-  },
-  "type": "object"
-}
    • addedInput schema / properties / policy_parameters
      Added value: +{
+  "additionalProperties": {},
+  "description": "Input parameters for this tool's decision function. For gpu:false nodes with a registered kernel, these are computed server-side when compute is \"auto\" or \"server\". See the tool's manifest for field names.",
+  "propertyNames": {
+    "type": "string"
+  },
+  "type": "object"
+}
  4. Added

TDQS

B3.1/5.0
Behavior4/5

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

Beyond the readOnly/idempotent annotations, the description discloses genuinely useful behavior: default server-side compute for gpu:false nodes, browser delegation URLs, transient processing with no storage/logging/retention, and an AP2 artifact export with execution_hash for chain provenance. It also warns to use synthetic/anonymised inputs, which is actionable safety context not in the annotations.

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

Conciseness2/5

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

The description is bloated with tangential material — EU AI Act dates, Digital Omnibus/Parliament approval timing, KYA-OS donation history, a URL and an FV-status receipt hash — that competes with the two sentences that actually describe tool behavior. Front-loading is weak because the operational content is buried after the regulatory preamble.

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

Completeness3/5

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

For a 4-parameter tool with no output schema and an open-ended policy_parameters object, the description covers compute routing, chaining and data-handling but never explains what the attestation check computes or what a result signifies. The invocation mechanics are covered; the decision semantics are not.

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 coverage is 100%, so the schema already documents compute, parent_hashes, parent_tool_ids and policy_parameters; the description's compute-mode sentence is largely redundant with the enum description. It adds nothing for policy_parameters beyond deferring to 'the tool's manifest', so it does not exceed the baseline.

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

Purpose3/5

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

The description opens by restating the title and labels itself an 'OpenChainGraph compute node (compliance_mandate)', but never states in plain terms what the check actually validates about an agent's identity/authorization attestation. The verb+resource is only recoverable from the name and title, not from the body text, which is dominated by provenance and regulatory metadata.

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

Usage Guidelines3/5

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

Usage is only implied through the pipeline lists ('Consumes upstream artifacts from: ...', 'Output feeds: ...'), which signal where it sits in a chain but give no explicit when-to-use or when-not-to-use guidance versus siblings like verify_input_attestations or validate_agent_obo_mandate. No alternatives are named.

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

All AINumbers Fintech Intelligence Suite toolsInspect
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.

Resources