Start an opt-in OpenChrome run ledger. Returns {run_id,status,pathless metadata}.
AI agents invoke oc_run_start 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.
Starting a Chrome browser automation run is an Execute action because it triggers external browser operations and establishes a session whose consequences are determined by what the AI agent does within that run. While the tool itself only initializes state, it enables downstream Execute and potentially Destructive actions.
From the tool's definition The tool 'oc_run_start' initiates a chrome browser run ledger, returning a run_id and status. Given the server context that 'Controls a real Chrome browser for AI agents', this tool begins automated browser operations whose effects depend on subsequent…
Documented attack patterns abuse exactly the kind of access oc_run_start 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 oc_run_start:
{
"version": "1",
"default": "deny",
"tools": {
"oc_run_start": {
"limits": [
{
"counter": "oc_run_start_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}oc_run_start 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.
Start an opt-in OpenChrome run ledger. Returns {run_id,status,pathless metadata}. 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 oc_run_start: 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.
oc_run_start 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 oc_run_start 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 oc_run_start. 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.
oc_run_start 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.