Open an image file as a new document
AI agents use photoshop_open_image to create or update resources in Photoshop MCP Windows-First — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Photoshop MCP Windows-First environment.
Opening an image file creates a new document in Photoshop, which is a Write-level action (creating new state). It does not delete or overwrite anything, does not execute arbitrary code, and has no financial implications. The blast radius is low since it only opens a file for editing without modifying the source file.
From the tool's definition Open an image file as a new document
Attacks that exploit this kind of access
Open an image file as a new document. It is categorised as a Write tool in the Photoshop MCP Windows-First MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Photoshop MCP Windows-First MCP server in PolicyLayer and add a rule for photoshop_open_image: 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 Photoshop MCP Windows-First. Nothing to install.
photoshop_open_image is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the photoshop_open_image 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 photoshop_open_image. 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.
photoshop_open_image is provided by the Photoshop MCP Windows-First MCP server (rookietopred02-gif/photoshop-mcp-windows-first). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the 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 →