AI agents invoke set_stage_position to trigger actions in mcpXL30. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Stage position control on a physical electron microscope moves mechanical components in the real world. This is an Execute action (triggering external physical operations) with high severity because improper stage motion could damage the specimen, the stage, or the microscope itself.
From the tool's definition Tool name 'set_stage_position' on a server controlling a Philips XL30 ESEM microscope with 'stage motion' listed as a sensitive parameter in the safety envelope.
Attacks that exploit this kind of access
set_stage_position. It is categorised as a Execute tool in the mcpXL30 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the mcpXL30 MCP server in PolicyLayer and add a rule for set_stage_position: 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.
set_stage_position is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the set_stage_position 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 set_stage_position. 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.
set_stage_position 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 →