Formally-verified injection/exfiltration detector for AI agents (MCP-02).
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns, and a recommended action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01.
The untrusted text/data to screen.
Optional: for MCP-01 envelope cross-check.
Optional: the agent's role/system prompt; helps calibrate.
Operating point. Default standard.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
Screen untrusted input for prompt/tool injection, exfiltration, and obfuscation before an agent consumes it. Returns a verdict (clean|suspicious|attack), probability, bits-at-risk (upper bound on adversarial capture per the Adversarial Landauer bound), matched canon patterns, and a recommended action (allow|sanitize|reject|escalate). Backed by Aristotle-verified theorems T-IB-02/T-IB-06/T-IB-01.
| Argument | Type | Description |
|---|---|---|
| input* | string | The untrusted text/data to screen. |
| agentId | string | Optional: for MCP-01 envelope cross-check. |
| context | string | Optional: the agent's role/system prompt; helps calibrate. |
| certainty | string | Operating point. Default standard. |
{
"type": "object",
"required": [
"input"
],
"properties": {
"input": {
"type": "string",
"maxLength": 200000,
"minLength": 1,
"description": "The untrusted text/data to screen."
},
"agentId": {
"type": "string",
"description": "Optional: for MCP-01 envelope cross-check."
},
"context": {
"type": "string",
"description": "Optional: the agent's role/system prompt; helps calibrate."
},
"certainty": {
"enum": [
"quick",
"standard",
"premium"
],
"type": "string",
"description": "Operating point. Default standard."
}
},
"additionalProperties": false
}Analyze an agent trace for the Gray Swan Wave 16 class: untrusted retrieved/tool output causing a tool call outside the user-declared per-turn allowlist. Returns trace counts, unauthorized tool-call evidence, canon mapping VC-AI-TOOL-0001, and claim-boundary guardrails. Backed by T-IB-25/T-IB-29/T-IB-36.
| Argument | Type | Description |
|---|---|---|
| trace | object | Single agent trace with user_prompt, allowed_tools, and events[]. |
| traces | array | Optional batch of agent traces. |
| targetName | string | Optional display name for the assessed target. |
{
"type": "object",
"properties": {
"trace": {
"type": "object",
"description": "Single agent trace with user_prompt, allowed_tools, and events[].",
"additionalProperties": true
},
"traces": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"description": "Optional batch of agent traces."
},
"targetName": {
"type": "string",
"description": "Optional display name for the assessed target."
}
},
"additionalProperties": false
}