Deterministic, numbered list of actionable elements on the page.
AI agents call oc_observe 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 retrieves and presents information about page elements in a structured format. It has no side effects—it does not execute actions, modify data, delete anything, or move money. It is a pure read operation that helps an agent understand the current state of a page before taking action.
From the tool's definition Tool name 'oc_observe' and description 'Deterministic, numbered list of actionable elements on the page' indicate observation/inspection of page content without modification.
Documented attack patterns abuse exactly the kind of access oc_observe 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_observe:
{
"version": "1",
"default": "deny",
"tools": {
"oc_observe": {}
}
}oc_observe 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.
Deterministic, numbered list of actionable elements on the page. 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_observe: 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_observe 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_observe 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_observe. 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_observe 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.