Generate a pytest Playwright test based on crawl data and a user instruction. Always call crawl_page first to get the crawl_data. Returns the path to the generated test file — pass it as test_file when calling run_test.
AI agents use write_test to create or update resources in QA Automation MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your QA Automation MCP Server environment.
This tool creates new test files based on crawl data and user instructions. While it writes data to the filesystem (a reversible operation), it does not execute code, delete data, or move money. The 'medium' severity reflects that malicious test generation could introduce unwanted automated behaviors, but the effect is contained within the test suite scope and the written files can be reviewed and deleted.
From the tool's definition Tool description states it 'Generate[s] a pytest Playwright test' and 'Returns the path to the generated test file'. The verb 'generate' and the action of creating a new test file indicates content creation/modification.
Attacks that exploit this kind of access
Generate a pytest Playwright test based on crawl data and a user instruction. Always call crawl_page first to get the crawl_data. Returns the path to the generated test file — pass it as test_file when calling run_test. It is categorised as a Write tool in the QA Automation MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the QA Automation MCP Server MCP server in PolicyLayer and add a rule for write_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.
write_test is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the write_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 write_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.
write_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.
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 →