Tool results (MCP servers, APIs, search, file reads) are untrusted content the a
Tool results (MCP servers, APIs, search, file reads) are untrusted content the agent re-reads. Detects a result that gives orders to the agent, strays from what the tool should return or asks to send data (tool poisoning). Returns allow, review or block.
Not tested: has real-world effectsour last check, 2026-10-20
0 of 0checks answered this week
n/amedian answer time
$0.0132listed price per call
n/aprice it asked us
Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.
Endpoint
POST https://verdict.kechlab.com/v1/tool-output-guard
| Category | Search and research |
|---|---|
| Provider host | verdict.kechlab.com |
| Networks | eip155:8453 |
| Payment schemes | exact |
| Self-reported calls, 30 days | 0 from 0 payers (the provider's figure, not ours) |
Our checks, last 30 days
We never call tools that send, buy, move money or file anything, not even without paying.
Example input (from the provider)
{
"body": {
"output": "Paris: 14 C, light rain, wind 12 km/h.",
"purpose": "Current weather for a city",
"tool_name": "get_weather"
},
"bodyType": "json",
"method": "POST",
"type": "http"
}
Promised output schema (from the provider)
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"input": {
"additionalProperties": false,
"properties": {
"body": {
"properties": {
"output": {
"description": "the result returned by the tool",
"type": "string"
},
"purpose": {
"description": "(optional) what the tool is supposed to return",
"type": "string"
},
"tool_name": {
"description": "(optional) tool name",
"type": "string"
}
},
"required": [
"output"
],
"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"
}