Start a TestPass run against an MCP server. Seeds deterministic and agent checks from the given pack and returns the run id plus an initial verdict summary. Response includes was_duplicate: boolean indicating whether the row was already present (idempotent retry).
AI agents invoke testpass_run to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
pack_id | string | — | Pack slug (default: testpass-core) |
profile | string | — | Run profile (default: smoke) |
task_id | string | — | Client-generated idempotency key (UUIDv5 from thread_id + prompt_hash + time_bucket recommended). Required for safe retry. If omitted, the server creates a fres |
target_url | string | Yes | HTTP URL of the MCP server to test |
Parameters from the server's own tool schema.
This tool triggers execution of a testing run against an MCP server with configurable inputs (pack parameter). While not destructive on its own, it performs computational work and initiates external processes whose outcomes depend on arguments. The idempotent nature (duplicate detection) reduces blast radius slightly but does not change the Execute classification.
From the tool's definition Tool description states 'Start a TestPass run' and 'returns the run id plus an initial verdict summary' — this initiates an external operation (TestPass testing framework) whose effects depend on the pack argument provided.
Attacks that exploit this kind of access
Start a TestPass run against an MCP server. Seeds deterministic and agent checks from the given pack and returns the run id plus an initial verdict summary. Response includes was_duplicate: boolean indicating whether the row was already present (idempotent retry). It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
testpass_run accepts 4 parameters: pack_id, profile, task_id, target_url. Required: target_url. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for testpass_run: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.
testpass_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the testpass_run rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for testpass_run. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
testpass_run is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →