AI agents use capture_image to create or update resources in mcpXL30 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your mcpXL30 environment.
This tool creates and persists new image files on the microscope console host's filesystem. While this is reversible (files can be deleted), it modifies the state of the system by adding new data. It does not execute arbitrary commands, destroy existing data, or involve financial transactions.
From the tool's definition The tool description explicitly states it will 'Write a TIFF image to a path visible to the XL30 console host.' This is a create/write operation that produces new data artifacts on the microscope's host system.
Attacks that exploit this kind of access
Write a TIFF image to a path visible to the XL30 console host. It is categorised as a Write tool in the mcpXL30 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the mcpXL30 MCP server in PolicyLayer and add a rule for capture_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 mcpXL30. Nothing to install.
capture_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 capture_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 capture_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.
capture_image is provided by the mcpXL30 MCP server (tspspi/mcpxl30). 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 →