Run each test individually with action capture and auto-save flows. Discovers all tests (optionally filtered by project/grep), skips tests that already have up-to-date flows, runs the rest one by one, and saves a flow for each passing test. Returns a summary of new, updated, up-to-date, and faile...
AI agents invoke e2e_build_flows to trigger actions in Playwright Autopilot. 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 triggers execution of arbitrary E2E tests in a browser context, which can perform any action a test defines—navigation, form submission, file uploads, keyboard input. While the tool itself doesn't delete data or move money, it executes external operations (tests) whose effects depend on test arguments.
From the tool's definition Tool performs 'Run each test individually' and 'runs the rest one by one', executing browser automation tests with side effects including capturing actions and auto-saving flows to disk.
Documented attack patterns abuse exactly the kind of access e2e_build_flows gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Playwright Autopilot, and nothing reaches the server without passing your rules. This is the rule we recommend for e2e_build_flows:
{
"version": "1",
"default": "deny",
"tools": {
"e2e_build_flows": {
"limits": [
{
"counter": "e2e_build_flows_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}e2e_build_flows stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run each test individually with action capture and auto-save flows. Discovers all tests (optionally filtered by project/grep), skips tests that already have up-to-date flows, runs the rest one by one, and saves a flow for each passing test. Returns a summary of new, updated, up-to-date, and failed flows. It is categorised as a Execute tool in the Playwright Autopilot MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Playwright Autopilot MCP server in PolicyLayer and add a rule for e2e_build_flows: 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 Playwright Autopilot. Nothing to install.
e2e_build_flows 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 e2e_build_flows 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 e2e_build_flows. 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.
e2e_build_flows is provided by the Playwright Autopilot MCP server (kaizen-yutani/playwright-autopilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Playwright Autopilot, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
51 Playwright Autopilot tools catalogued and risk-classified — across an index of 43,000+ MCP servers.