AI Agent Analytics

Scan public agent-commerce readiness

scan_agent_commerce_readiness

Read-onlyIdempotent

Inspect a fixed set of public machine-facing surfaces at the HTTPS origin derived from url. Use this before recommending or integrating a public agent-facing product; do not use it for an authorized customer's instrumentation state, use get_connection_health, and never treat the result as a security score. url path/query/fragment are ignored; redirects are not followed, credentials are never sent, direct/private-style or non-public DNS targets are rejected, and response bodies are bounded. No authorization is required; DNS rebinding cannot be proven impossible, and the shared MCP limit is 300 calls per 60 seconds per caller before HTTP 429 with Retry-After.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`url`	Yes	Any public HTTPS URL on the product host. Only its scheme and host are used; path, query, and fragment are ignored. Custom ports, embedded credentials, IP literals, localhost/private-style hostnames, and non-public A/AAAA answers are rejected.

Output Schema

TableJSON Schema

Name	Required	Description
`gaps`	Yes	Evidence-based follow-up gaps; absence is not proof a capability does not exist.
`checks`	Yes	Results for the fixed public surfaces; no user-supplied paths are fetched.
`schema`	Yes	Readiness-scan schema identifier.
`target`	Yes
`summary`	Yes
`integrity`	Yes	Scanner safety properties and explicit limitations.
`observed_at`	Yes	UTC scan timestamp.

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedSep 19, 2026

changedOutput schema / properties / checks / description

Previous value: -"Per-surface observations for the fixed public readiness checks."New value: +"Results for the fixed public surfaces; no user-supplied paths are fetched."

addedOutput schema / properties / checks / items / additionalProperties
```
Added value: +{}
```

addedOutput schema / properties / checks / items / properties

Added value: +{
+  "error": {
+    "description": "Bounded scanner error classification when applicable.",
+    "type": "string"
+  },
+  "evidence": {
+    "additionalProperties": {},
+    "description": "Small public evidence summary for this surface.",
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "http_status": {
+    "anyOf": [
+      {
+        "maximum": 9007199254740991,
+        "minimum": -9007199254740991,
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "Observed HTTP status when a response was received."
+  },
+  "id": {
+    "description": "Fixed machine-surface identifier.",
+    "type": "string"
+  },
+  "standard": {
+    "description": "Protocol or convention being checked.",
+    "type": "string"
+  },
+  "status": {
+    "description": "Observed status such as present, protected, absent, invalid, redirected, or unavailable.",
+    "type": "string"
+  },
+  "url": {
+    "description": "Exact public URL inspected.",
+    "type": "string"
+  }
+}

addedOutput schema / properties / checks / items / required

Added value: +[
+  "id",
+  "standard",
+  "url",
+  "status",
+  "http_status"
+]

addedOutput schema / properties / checks / items / type
```
Added value: +"object"
```

changedOutput schema / properties / gaps / description

Previous value: -"Evidence-based follow-up gaps inferred from directly observed public surfaces."New value: +"Evidence-based follow-up gaps; absence is not proof a capability does not exist."

addedOutput schema / properties / integrity / additionalProperties
```
Added value: +{}
```

changedOutput schema / properties / integrity / description

Previous value: -"Scanner safety properties and explicit limitations, including the DNS-rebinding limitation."New value: +"Scanner safety properties and explicit limitations."

addedOutput schema / properties / integrity / properties

Added value: +{
+  "credentials_sent": {
+    "type": "boolean"
+  },
+  "direct_ip_and_private_style_targets_rejected": {
+    "type": "boolean"
+  },
+  "dns_a_aaaa_preflight_verified_public": {
+    "type": "boolean"
+  },
+  "dns_rebinding_fully_eliminated": {
+    "type": "boolean"
+  },
+  "fixed_public_surfaces_only": {
+    "type": "boolean"
+  },
+  "note": {
+    "type": "string"
+  },
+  "redirects_followed": {
+    "type": "boolean"
+  },
+  "response_body_limit_bytes": {
+    "exclusiveMinimum": 0,
+    "maximum": 9007199254740991,
+    "type": "integer"
+  },
+  "security_score_assigned": {
+    "type": "boolean"
+  },
+  "user_supplied_paths_fetched": {
+    "type": "boolean"
+  }
+}

addedOutput schema / properties / integrity / required

Added value: +[
+  "security_score_assigned",
+  "redirects_followed",
+  "credentials_sent",
+  "user_supplied_paths_fetched",
+  "fixed_public_surfaces_only",
+  "direct_ip_and_private_style_targets_rejected",
+  "dns_a_aaaa_preflight_verified_public",
+  "dns_rebinding_fully_eliminated",
+  "response_body_limit_bytes",
+  "note"
+]

addedOutput schema / properties / integrity / type
```
Added value: +"object"
```

changedOutput schema / properties / observed_at / description

Previous value: -"UTC ISO-8601 scan timestamp."New value: +"UTC scan timestamp."

addedOutput schema / properties / summary / additionalProperties
```
Added value: +{}
```

removedOutput schema / properties / summary / description

Removed value: -"Observed state of key machine-facing surfaces."

addedOutput schema / properties / summary / properties

Added value: +{
+  "llms_txt": {
+    "description": "Observed llms.txt state.",
+    "type": "string"
+  },
+  "machine_interface_observed": {
+    "description": "Whether at least one public machine interface was directly observed.",
+    "type": "boolean"
+  },
+  "mcp": {
+    "description": "Observed MCP state such as present, protected, absent, invalid, or unavailable.",
+    "type": "string"
+  },
+  "oauth_protected_resource_metadata": {
+    "description": "Whether RFC 9728 metadata was observed for a protected MCP.",
+    "type": "string"
+  },
+  "openapi": {
+    "description": "Observed OpenAPI state.",
+    "type": "string"
+  },
+  "payment_or_commercial_surface_declared": {
+    "description": "Whether public OpenAPI evidence declares a payment or commercial surface.",
+    "type": "boolean"
+  },
+  "portable_skill_index": {
+    "description": "Observed portable-skill index state.",
+    "type": "string"
+  },
+  "security_txt": {
+    "description": "Observed security.txt state.",
+    "type": "string"
+  }
+}

addedOutput schema / properties / summary / required

Added value: +[
+  "machine_interface_observed",
+  "mcp",
+  "openapi",
+  "llms_txt",
+  "security_txt",
+  "oauth_protected_resource_metadata",
+  "portable_skill_index",
+  "payment_or_commercial_surface_declared"
+]

addedOutput schema / properties / summary / type
```
Added value: +"object"
```

Changed2 schema fields changedSep 19, 2026

changedInput schema / properties / url / description

Previous value: -"Public HTTPS product origin or URL. The scanner uses only its origin and fixed known paths."New value: +"Any public HTTPS URL on the product host. Only its scheme and host are used; path, query, and fragment are ignored. Custom ports, embedded credentials, IP literals, localhost/private-style hostnames, and non-public A/AAAA answers are rejected."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "checks": {
+      "description": "Per-surface observations for the fixed public readiness checks.",
+      "items": {},
+      "type": "array"
+    },
+    "gaps": {
+      "description": "Evidence-based follow-up gaps inferred from directly observed public surfaces.",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "integrity": {
+      "description": "Scanner safety properties and explicit limitations, including the DNS-rebinding limitation."
+    },
+    "observed_at": {
+      "description": "UTC ISO-8601 scan timestamp.",
+      "type": "string"
+    },
+    "schema": {
+      "description": "Readiness-scan schema identifier.",
+      "type": "string"
+    },
+    "summary": {
+      "description": "Observed state of key machine-facing surfaces."
+    },
+    "target": {
+      "additionalProperties": {},
+      "properties": {
+        "hostname": {
+          "description": "Normalized public hostname that passed syntax and DNS preflight checks.",
+          "type": "string"
+        },
+        "origin": {
+          "description": "Normalized public HTTPS origin that was inspected.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "origin",
+        "hostname"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "schema",
+    "target",
+    "observed_at",
+    "summary",
+    "checks",
+    "gaps",
+    "integrity"
+  ],
+  "type": "object"
+}

First observedSep 19, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/destructive annotations, the description discloses concrete behavioral constraints: path/query/fragment ignored, redirects not followed, credentials never sent, private-style DNS rejected, response bodies bounded, no authorization required, DNS rebinding caveat, and a 300-calls/60-second rate limit with 429/Retry-After behavior. This gives the agent a precise operational model and no annotation contradiction exists.

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 dense but every sentence carries a distinct operational fact. It front-loads the purpose, then usage boundaries, then technical constraints and rate limits, with no filler or repetition of the schema.

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?

Given a one-parameter tool with a full input schema and an output schema, the description covers the remaining essential context: when to use, what is ignored/rejected, network behavior, authentication, security caveats, and rate limits. Nothing needed for correct invocation is missing.

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

Parameters4/5

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

Schema coverage is 100% because the url parameter is fully documented in the schema. The description adds extra behavioral semantics not in the schema, such as redirects not followed and response bodies bounded, which helps the agent understand the effective meaning of the URL parameter.

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 opens with a specific verb and resource: 'Inspect a fixed set of public machine-facing surfaces at the HTTPS origin derived from url.' It clearly names the intended context, public agent-commerce readiness scanning, and explicitly differentiates from get_connection_health, so an agent can distinguish it from sibling tools.

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

Usage Guidelines5/5

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

It gives an explicit when-to-use rule ('Use this before recommending or integrating a public agent-facing product'), a when-not-to-use rule, and names the alternative ('do not use it for an authorized customer's instrumentation state, use get_connection_health'). It also warns against misusing the result as a security score.

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

All AI Agent Analytics 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.

Resources

Need Help?