AI agents use export_layer to create or update resources in PS-MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your PS-MCP environment.
The tool creates new exported layer files or data, which constitutes data creation (Write category). Severity is medium because while the exported data is reversible and doesn't destroy existing content, exporting could overwrite existing files or consume storage resources, and in an automated AI context could create unexpected outputs that require cleanup.
From the tool's definition export_layer exports/writes layer data from an Adobe Photoshop document, creating new output files or data artifacts. Combined with sibling tools like export_doc that export documents, this performs file generation and data creation operations.
Attacks that exploit this kind of access
Args:. It is categorised as a Write tool in the PS-MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the PS- MCP server in PolicyLayer and add a rule for export_layer: 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 PS-MCP. Nothing to install.
export_layer 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 export_layer 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 export_layer. 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.
export_layer is provided by the PS- MCP server (pangxie231/ps-mcp). 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 →