Evaluates a JavaScript expression in the current context. If execution is paused, it automatically evaluates in the paused call frame context.
AI agents invoke evaluate_script to trigger actions in MiniApp CDP 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 arbitrary JavaScript in a running WeChat MiniApp context via Chrome DevTools Protocol. An AI agent could use it to run any code — exfiltrate data, manipulate app state, invoke sensitive APIs, or escalate to destructive/financial actions within the app.
From the tool's definition "Evaluates a JavaScript expression in the current context" — runs arbitrary JavaScript code in a live browser/MiniApp runtime environment
Documented attack patterns abuse exactly the kind of access evaluate_script gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MiniApp CDP MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for evaluate_script:
{
"version": "1",
"default": "deny",
"tools": {
"evaluate_script": {
"limits": [
{
"counter": "evaluate_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}evaluate_script 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.
Evaluates a JavaScript expression in the current context. If execution is paused, it automatically evaluates in the paused call frame context. It is categorised as a Execute tool in the MiniApp CDP MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MiniApp CDP MCP server in PolicyLayer and add a rule for evaluate_script: 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 MiniApp CDP MCP. Nothing to install.
evaluate_script 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 evaluate_script 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 evaluate_script. 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.
evaluate_script is provided by the MiniApp CDP MCP server (zhizhuodemao/miniapp-cdp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 18 MiniApp CDP MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
18 MiniApp CDP MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.