screen_parse

Use OmniParser V2 to detect all UI elements on screen via YOLO + OCR + Florence-2.

Server MacWright ruchit-p/macwright
Category Read
Risk class Low
Parameters 00 required

What screen_parse does on MacWright

AI agents call screen_parse to retrieve information from MacWright without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why screen_parse needs a policy

This tool captures and parses the current screen state to identify UI elements using computer vision and OCR. It only reads/analyzes visual data without modifying anything. Severity is medium because it can capture sensitive on-screen information (passwords, private data) visible at the time of invocation.

From the tool's definition 'detect all UI elements on screen via YOLO + OCR + Florence-2' — purely reads/analyzes screen content

Questions about screen_parse

What does the screen_parse tool do? +

Use OmniParser V2 to detect all UI elements on screen via YOLO + OCR + Florence-2. It is categorised as a Read tool in the MacWright MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on screen_parse? +

Register the MacWright MCP server in PolicyLayer and add a rule for screen_parse: 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 MacWright. Nothing to install.

What risk level is screen_parse? +

screen_parse is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit screen_parse? +

Yes. Add a rate_limit block to the screen_parse 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.

How do I block screen_parse completely? +

Set action: deny in the PolicyLayer policy for screen_parse. 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.

What MCP server provides screen_parse? +

screen_parse is provided by the MacWright MCP server (ruchit-p/macwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.