Find elements using vision-based screenshot analysis. Returns annotated screenshot with numbered elements.
AI agents call vision_find 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.
The tool reads and analyzes the current browser screen via screenshot, returning annotated visual data. It does not modify state, execute code, or perform writes. However, it operates within a live browser context that could expose sensitive on-screen data (e.g., authenticated sessions, personal info), warranting medium severity.
From the tool's definition Find elements using vision-based screenshot analysis. Returns annotated screenshot with numbered elements.
Documented attack patterns abuse exactly the kind of access vision_find 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 vision_find:
{
"version": "1",
"default": "deny",
"tools": {
"vision_find": {}
}
}vision_find 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.
Find elements using vision-based screenshot analysis. Returns annotated screenshot with numbered elements. 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 vision_find: 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.
vision_find 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 vision_find 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 vision_find. 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.
vision_find 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.