Auxiliary action: allows executing specified JS in the page (simulate click/scroll/input, etc.) to trigger requests.
AI agents invoke execute_page_action to trigger actions in Ruishu 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 enables execution of arbitrary JavaScript within a browser page context. While the stated purpose is to simulate user interactions (click, scroll, input), the ability to execute arbitrary JS means an AI agent could perform unintended actions including modifying page state, accessing sensitive data, exfiltrating information, or triggering malicious requests. This falls squarely into the Execute category.
From the tool's definition Tool description explicitly states it 'allows executing specified JS in the page' and can 'simulate click/scroll/input, etc.
Documented attack patterns abuse exactly the kind of access execute_page_action gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ruishu MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for execute_page_action:
{
"version": "1",
"default": "deny",
"tools": {
"execute_page_action": {
"limits": [
{
"counter": "execute_page_action_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}execute_page_action 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.
Auxiliary action: allows executing specified JS in the page (simulate click/scroll/input, etc.) to trigger requests. It is categorised as a Execute tool in the Ruishu MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ruishu MCP server in PolicyLayer and add a rule for execute_page_action: 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 Ruishu MCP. Nothing to install.
execute_page_action 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 execute_page_action 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 execute_page_action. 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.
execute_page_action is provided by the Ruishu MCP server (xuange520/ruishu-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Ruishu MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 Ruishu MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.