AI agents call assert_status to retrieve information from Assert without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the state of an already-running test and returns status information and results. It performs no modifications, deletions, or external operations; it only retrieves and displays data about completed or in-progress test runs. This is a straightforward Read operation with minimal risk.
From the tool's definition Tool name 'assert_status' and description 'Poll a test run for its current status' indicate a read operation that retrieves test results and status information.
Attacks that exploit this kind of access
Poll a test run for its current status and step-level results. Returns pass/fail with actionable failure details and screenshot URLs for failed steps. It is categorised as a Read tool in the Assert MCP Server, which means it retrieves data without modifying state.
Register the Assert MCP server in PolicyLayer and add a rule for assert_status: 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 Assert. Nothing to install.
assert_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the assert_status 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 assert_status. 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.
assert_status is provided by the Assert MCP server (pixel-funnel/assert-click-mcp). 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 →