Run a UI/UX quality check synchronously against a URL. Executes the deterministic uxpass-core check set (HTTP, HTML, accessibility, agent readability, performance, security) against the target and returns the run id, status, UX Score, and summary. Pass either url (a one-off check) or pack_name (r...
AI agents invoke uxpass_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 |
|---|---|---|---|
url | string | — | Target URL for a one-off run (takes precedence over pack_name) |
hats | array | — | Reserved for future use. Currently ignored; the deterministic runner evaluates the full uxpass-core check set on every run. |
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 |
pack_name | string | — | Name of a registered UXPass pack; the pack's url is used as the target |
Parameters from the server's own tool schema.
This tool triggers external operations (automated testing/scanning of arbitrary URLs) whose effects depend on the URL argument provided. The tool runs code-like operations (quality checks, security checks) against target systems, which is characteristic of Execute category.
From the tool's definition Tool executes deterministic checks "against a URL" and "returns the run id, status" indicating active operations performed on external systems.
Risk signalsAccepts URL/endpoint input (url)
Attacks that exploit this kind of access
Run a UI/UX quality check synchronously against a URL. Executes the deterministic uxpass-core check set (HTTP, HTML, accessibility, agent readability, performance, security) against the target and returns the run id, status, UX Score, and summary. Pass either url (a one-off check) or pack_name (resolves the registered pack's url). The hats parameter is accepted for forward compatibility but is currently ignored; LLM hats land in a later chunk. 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.
uxpass_run accepts 4 parameters: url, hats, task_id, pack_name. 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 uxpass_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.
uxpass_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 uxpass_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 uxpass_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.
uxpass_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 →