Inspects Model Context Protocol (MCP) tool definitions, JSON schemas, and server
Inspects Model Context Protocol (MCP) tool definitions, JSON schemas, and server cards for hidden instructions, tool shadowing, and data exfiltration vectors.
Answeringour last check, 2026-10-18
1 of 1checks answered this week
474 msmedian answer time
$0.01listed price per call
$0.01price it asked us
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
POST https://canaryguard-402.onrender.com/v1/mcp-tool-auditor
| Category | Everything else |
|---|---|
| Provider host | canaryguard-402.onrender.com |
| Networks | eip155:8453, solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp |
| Payment schemes | exact |
| Self-reported calls, 30 days | 4 from 2 payers (the provider's figure, not ours) |
Our checks, last 30 days
| Day | Result | HTTP | Asked | Time |
|---|---|---|---|---|
| 2026-10-18 | valid payment request | 402 | $0.01 | 474 ms |
Example input (from the provider)
{
"body": {
"tool_description": "Deterministic prompt-injection firewall",
"tool_name": "canary_sanitize"
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"tool_name": {
"type": "string"
}
},
"required": [
"tool_name"
],
"type": "object"
},
"bodyType": {
"enum": [
"json",
"form-data",
"text"
],
"type": "string"
},
"method": {
"enum": [
"POST"
],
"type": "string"
},
"type": {
"const": "http",
"type": "string"
}
},
"required": [
"type",
"method",
"bodyType",
"body"
],
"type": "object"
},
"output": {
"properties": {
"example": {
"type": "object"
},
"type": {
"type": "string"
}
},
"required": [
"type"
],
"type": "object"
}
},
"required": [
"input"
],
"type": "object"
}