Register a JavaScript script to execute automatically on every page load. This is useful for persistent hooks (like XHR interceptors, fetch interceptors, etc.) that need to survive page refreshes. The script will execute before any other scripts on the page, making it ideal for: - Intercepting ne...
AI agents invoke add_persistent_script to trigger actions in ReverseCraft DevTools 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 on every page load, before any other scripts. It can intercept network requests, modify global objects/prototypes, and set up hooks — all powerful operations with broad blast radius. Since the injected script persists across page loads and runs with high privilege, misuse could lead to credential theft, data exfiltration, or manipulation of page behavior.
From the tool's definition Register a JavaScript script to execute automatically on every page load... The script will execute before any other scripts on the page... Intercepting network requests, Modifying global objects or prototypes, Setting up debugging hooks
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access add_persistent_script gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ReverseCraft DevTools MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add_persistent_script:
{
"version": "1",
"default": "deny",
"tools": {
"add_persistent_script": {
"limits": [
{
"counter": "add_persistent_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}add_persistent_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.
Register a JavaScript script to execute automatically on every page load. This is useful for persistent hooks (like XHR interceptors, fetch interceptors, etc.) that need to survive page refreshes. The script will execute before any other scripts on the page, making it ideal for: - Intercepting network requests (XMLHttpRequest, fetch) - Modifying global objects or prototypes - Setting up debugging hooks Returns a unique identifier that can be used to remove the script later. It is categorised as a Execute tool in the ReverseCraft DevTools MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ReverseCraft DevTools MCP server in PolicyLayer and add a rule for add_persistent_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 ReverseCraft DevTools MCP. Nothing to install.
add_persistent_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 add_persistent_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 add_persistent_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.
add_persistent_script is provided by the ReverseCraft DevTools MCP server (reverse-craft/rc-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ReverseCraft DevTools 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.
46 ReverseCraft DevTools MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.