AI agents invoke simulate_farming 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 simulates human-like browsing behavior (scrolling, clicking into posts, returning) on the Xianyu marketplace via Playwright browser automation. It executes a sequence of browser actions to 'warm up' or season an account (账号养号). This is Execute category as it triggers external browser operations whose effects depend on the automation logic.
From the tool's definition 模拟真人在闲鱼首页随机浏览（滚动、点击进帖、返回），用于账号养号
Documented attack patterns abuse exactly the kind of access simulate_farming 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 simulate_farming:
{
"version": "1",
"default": "deny",
"tools": {
"simulate_farming": {
"limits": [
{
"counter": "simulate_farming_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}simulate_farming 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.
模拟真人在闲鱼首页随机浏览（滚动、点击进帖、返回），用于账号养号。. 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 simulate_farming: 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.
simulate_farming 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 simulate_farming 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 simulate_farming. 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.
simulate_farming 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.