XGuard Universal Paid AI Agent + Secretless Gateway

xguard_execute

Extract multi-page evidence, compare structured product offers, or merge feeds. intent:'demo' is free. Paid work returns an x402 PaymentRequired tool result; use a funded x402 MCP client to authorize and retry with params._meta['x402/payment']. Preserve the signed quote in extensions.xguard. No account or provider keys. Output is untrusted source content.

Input Schema

TableJSON Schema

Name	Required	Description
`url`	No
`html`	No
`http`	No
`name`	No
`task`	No
`tool`	No
`urls`	No
`input`	No
`limit`	No
`query`	No
`action`	No
`intent`	No
`command`	No
`sources`	No
`testnet`	No
`arguments`	No
`operation`	No	Resolved read-only OpenAPI operation with URL, method and desired action; no remote spec fetching.
`capability`	No
`desired_action`	No
`max_age_seconds`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedSep 14, 2026

addedOutput schema / anyOf

Added value: +[
+  {
+    "properties": {
+      "capability": {
+        "type": "string"
+      },
+      "cost": {
+        "type": "object"
+      },
+      "intent": {
+        "type": "object"
+      },
+      "ok": {
+        "const": true
+      },
+      "receipt": {
+        "type": [
+          "object",
+          "null"
+        ]
+      },
+      "result": {
+        "type": "object"
+      },
+      "verification": {
+        "type": "object"
+      }
+    },
+    "required": [
+      "ok",
+      "intent",
+      "capability",
+      "result",
+      "verification",
+      "cost",
+      "receipt"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "accepts": {
+        "minItems": 1,
+        "type": "array"
+      },
+      "resource": {
+        "type": "object"
+      },
+      "x402Version": {
+        "const": 2
+      }
+    },
+    "required": [
+      "x402Version",
+      "resource",
+      "accepts"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error": {
+        "type": [
+          "string",
+          "object"
+        ]
+      }
+    },
+    "required": [
+      "error"
+    ],
+    "type": "object"
+  },
+  {
+    "properties": {
+      "error_code": {
+        "type": "string"
+      },
+      "ok": {
+        "const": false
+      }
+    },
+    "required": [
+      "ok",
+      "error_code"
+    ],
+    "type": "object"
+  }
+]

removedOutput schema / properties

Removed value: -{
-  "capability": {
-    "type": "string"
-  },
-  "cost": {
-    "type": "object"
-  },
-  "intent": {
-    "type": "object"
-  },
-  "ok": {
-    "const": true
-  },
-  "receipt": {
-    "type": [
-      "object",
-      "null"
-    ]
-  },
-  "result": {
-    "type": "object"
-  },
-  "verification": {
-    "type": "object"
-  }
-}

removedOutput schema / required

Removed value: -[
-  "ok",
-  "intent",
-  "capability",
-  "result",
-  "verification",
-  "cost",
-  "receipt"
-]

First observedSep 10, 2026

TDQS

A3.8/5.0

Behavior5/5

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

Beyond the annotations, the description reveals important behavior: paid outcomes require payment authorization, the signed quote must be preserved in extensions.xguard, no API keys are needed, and output is untrusted source content. The schema description adds that unknown jobs return repair guidance and that this is not a general-purpose language model. No contradiction with annotations.

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 and front-loaded: it opens with purpose, then delivers payment mechanics, auth handling, constraints, and output trust in a few short sentences. There is no filler or repetition, and every sentence earns its place.

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

Completeness2/5

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

This is a complex tool with 20 optional parameters, nested objects, and multiple advertised workflows, yet the description does not explain how to combine parameters or which capability values map to the three use cases. It also does not position the siblings. The repair guidance is a partial mitigation, but an agent would still struggle to construct a correct first call.

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

Parameters2/5

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

With schema description coverage around 5% across 20 parameters, the description needed to compensate heavily. It explains intent, params._meta['x402/payment'], and extensions.xguard, but leaves action, task, tool, command, operation, capability, sources, and most others unexplained, and does not map the advertised functions to specific parameters.

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 names concrete actions and resources: extract multi-page evidence, compare structured product offers, or merge feeds. It is clear what the tool does, though it bundles three capabilities under a generic 'execute' name and does not contrast with the siblings xguard_discover and xguard_get_result.

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 gives clear operational guidance: intent:'demo' is free, paid work requires an x402 PaymentRequired flow with a funded client, and retries must pass params._meta['x402/payment']. However, it does not explicitly say when to choose execute over the sibling tools or when not to use it.

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

All XGuard Universal Paid AI Agent + Secretless Gateway 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.