AI agents use set_stigmator 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.
A stigmator is an electromagnetic lens component used to correct astigmatism in electron microscopes. 'set_' prefix implies a write/adjustment operation on beam parameters. This is reversible (you can re-adjust), so Write is appropriate. Severity is medium because misconfiguration could degrade image quality or require recalibration, but it's unlikely to cause hardware damage or irreversible harm.
From the tool's definition Tool name 'set_stigmator' suggests setting/adjusting a stigmator (beam correction component); description is empty and uninformative.
Attacks that exploit this kind of access
set_stigmator. 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 set_stigmator: 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_stigmator 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 set_stigmator 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_stigmator. 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_stigmator 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 →