AI agents invoke restart_browser to trigger actions in FishClaw MCP. 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 a browser process restart command via Playwright. While not directly destructive or writing data, restarting browser processes can affect ongoing operations, session state, and marketplace interactions. The action is an external operation whose effects depend on the system state.
From the tool's definition Tool description states it 'reinitializes Playwright browser process' (重新初始化 Playwright 浏览器进程), which is a browser automation action that triggers external operations.
Documented attack patterns abuse exactly the kind of access restart_browser gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FishClaw MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for restart_browser:
{
"version": "1",
"default": "deny",
"tools": {
"restart_browser": {
"limits": [
{
"counter": "restart_browser_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}restart_browser 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.
重新初始化 Playwright 浏览器进程，无需重启 MCP 服务器。. It is categorised as a Execute tool in the FishClaw MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the FishClaw MCP server in PolicyLayer and add a rule for restart_browser: 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 FishClaw MCP. Nothing to install.
restart_browser 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 restart_browser 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 restart_browser. 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.
restart_browser is provided by the FishClaw MCP server (tnoobt/fishclaw_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from FishClaw MCP, 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.
12 FishClaw MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.