AI agents invoke run_script to trigger actions in Search. 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 scripts whose effects depend entirely on the script content provided by the caller. While individual browser actions (click, fill) might be Write operations, script execution is Execute because it can trigger arbitrary side effects through browser automation, including navigation, form submission, data exfiltration, or other uncontrolled operations.
From the tool's definition Tool name 'run_script' combined with description 'Run a script on this' indicates execution of arbitrary scripts.
Documented attack patterns abuse exactly the kind of access run_script gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. This is the rule we recommend for run_script:
{
"version": "1",
"default": "deny",
"tools": {
"run_script": {
"limits": [
{
"counter": "run_script_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_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.
Run a script on this. It is categorised as a Execute tool in the Search MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Search MCP server in PolicyLayer and add a rule for run_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 Search. Nothing to install.
run_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 run_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 run_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.
run_script is provided by the Search MCP server (@agent-infra/mcp-server-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Search, 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.
36 Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.