Find the commit that broke a test using behavioral bisection. Runs binary search through git history, comparing action captures to identify what changed. Uses git worktrees (never modifies your working tree).
AI agents invoke e2e_bisect 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.
The tool actively executes git operations, spawns test runners across multiple commits, and drives browser automation to compare behavioral captures. While it claims 'never modifies your working tree', it still executes arbitrary code from different commits in worktrees, making it an Execute-category tool with high severity due to the potential for running untrusted code from git history and the broad system access…
From the tool's definition 'Runs binary search through git history, comparing action captures' and 'Uses git worktrees' — this tool executes git commands, spawns processes to run tests across commit history, and performs browser automation actions repeatedly during bisection
Documented attack patterns abuse exactly the kind of access e2e_bisect 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_bisect:
{
"version": "1",
"default": "deny",
"tools": {
"e2e_bisect": {
"limits": [
{
"counter": "e2e_bisect_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}e2e_bisect 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.
Find the commit that broke a test using behavioral bisection. Runs binary search through git history, comparing action captures to identify what changed. Uses git worktrees (never modifies your working tree). 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_bisect: 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_bisect 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_bisect 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_bisect. 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_bisect 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.