Run the generated pytest Playwright test. Automatically heals the test if it fails due to a locator error. Always call write_test first.
AI agents invoke run_test to trigger actions in QA Automation MCP Server. 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.
This tool executes test code against web applications via Playwright, which can trigger arbitrary browser actions (clicks, form submissions, navigation, etc.) whose effects depend on the test content generated by the LLM. While the description doesn't explicitly mention destructive capabilities, Playwright tests have the potential to modify application state depending on what the generated tests do.
From the tool's definition Tool description states 'Run the generated pytest Playwright test' and 'Automatically heals the test if it fails'. This executes Playwright-based tests which can perform browser automation actions.
Attacks that exploit this kind of access
Run the generated pytest Playwright test. Automatically heals the test if it fails due to a locator error. Always call write_test first. It is categorised as a Execute tool in the QA Automation MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the QA Automation MCP Server MCP server in PolicyLayer and add a rule for run_test: 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 QA Automation MCP Server. Nothing to install.
run_test 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 run_test 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 run_test. 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.
run_test is provided by the QA Automation MCP Server MCP server (parajuliminiyan/playwrightmcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
run_test is one line of QA Automation MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →