AI agents invoke worker to trigger actions in OpenChrome. 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.
Managing workers in a browser automation framework implies spawning, stopping, or controlling execution agents/lanes. This falls under Execute as it controls operational processes. Severity is high because misuse could spin up or kill parallel browser automation workers at scale. Confidence is moderate because the description is minimal ('Manage workers. Actions:' is incomplete).
From the tool's definition 'Manage workers' — workers are execution units in a parallel automation context (given sibling tools like 'batch_execute', 'crawl', 'act')
Documented attack patterns abuse exactly the kind of access worker gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenChrome, and nothing reaches the server without passing your rules. This is the rule we recommend for worker:
{
"version": "1",
"default": "deny",
"tools": {
"worker": {
"limits": [
{
"counter": "worker_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}worker 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.
Manage workers. Actions:. It is categorised as a Execute tool in the OpenChrome MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenChrome MCP server in PolicyLayer and add a rule for worker: 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 OpenChrome. Nothing to install.
worker 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 worker 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 worker. 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.
worker is provided by the OpenChrome MCP server (shaun0927/openchrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 106 OpenChrome tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
106 OpenChrome tools catalogued and risk-classified — across an index of 42,500+ MCP servers.