AI agents call oc_policy to retrieve information from OpenChrome without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to be a diagnostic utility for querying or viewing the safety policy configuration of the OpenChrome system. There is no indication of the ability to modify policies, execute code, delete data, or trigger external operations. The action of inspecting a policy is a benign read operation with minimal security risk.
From the tool's definition The tool name is 'oc_policy' and the description states 'Inspect deterministic OpenChrome safety policy' with 'Use action='. The verb 'inspect' indicates read-only retrieval of policy information without modification or execution of external commands.
Documented attack patterns abuse exactly the kind of access oc_policy 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_policy:
{
"version": "1",
"default": "deny",
"tools": {
"oc_policy": {}
}
}oc_policy is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Inspect deterministic OpenChrome safety policy. Use action=. It is categorised as a Read tool in the OpenChrome MCP Server, which means it retrieves data without modifying state.
Register the OpenChrome MCP server in PolicyLayer and add a rule for oc_policy: 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_policy is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the oc_policy 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_policy. 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_policy 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.