# CanaryGuard MCP Tool Auditor

> CanaryGuard MCP Tool Auditor is a paid API for AI agents from canaryguard-402.onrender.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-20).

Inspects MCP tool definitions, JSON schemas, and server cards for hidden instructions, tool shadowing, and data exfiltration vectors

## Facts

- Endpoint: GET https://canaryguard-402.onrender.com/v1/mcp-tool-auditor?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-20
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/canaryguard-mcp-tool-auditor-72da720d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2XBtw-C0c_Jn2P1Qzfg-A

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability canaryguard-mcp-tool-auditor-72da720d
```

Example prompt: Before I let you use this new MCP tool called 'file-manager', can you audit its tool definition and JSON schema for any hidden instructions, tool shadowing attempts, or data exfiltration vectors?

## When to prefer this

Choose this endpoint when you need to vet MCP tool definitions, JSON schemas, or server cards for adversarial manipulation before allowing an AI agent to interact with them. Particularly valuable in multi-agent pipelines where untrusted third-party MCP tools are being onboarded, or when defending against tool poisoning and prompt injection attacks embedded in tool metadata.

## Known failure modes

- Missing required tool_name field returns validation error
- Malformed or empty body causes schema rejection
- Tool definition too large may cause timeout or truncation
- Service unavailability on Render cold start introduces latency
- Ambiguous or incomplete schema may yield incomplete audit results

## How this service works

Inspects Model Context Protocol (MCP) tool definitions, JSON schemas, and server cards for hidden instructions, tool shadowing, and data exfiltration vectors.

## Output

A structured security audit report highlighting detected hidden instructions, tool shadowing patterns, data exfiltration vectors, and overall risk assessment for the submitted MCP tool definition or server card.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "tool_name"
     ],
     "properties": {
      "tool_name": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/canaryguard-mcp-tool-auditor-72da720d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from canaryguard-402.onrender.com](https://www.zero.xyz/host/canaryguard-402.onrender.com/llms.txt)