AI agents call read_high_tension to retrieve information from mcpXL30 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries the current state of a measurable parameter (high tension voltage). It performs no write operations, does not execute commands that could damage equipment, and does not modify any settings. While it relates to a sensitive parameter (high tension), reading its value poses minimal risk compared to actually controlling it.
From the tool's definition Tool name is 'read_high_tension' and description states 'Fetch the latest measured high tension voltage' — both indicate retrieval of sensor data with no modification or control of equipment parameters.
Attacks that exploit this kind of access
Fetch the latest measured high tension voltage. It is categorised as a Read tool in the mcpXL30 MCP Server, which means it retrieves data without modifying state.
Register the mcpXL30 MCP server in PolicyLayer and add a rule for read_high_tension: 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.
read_high_tension is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the read_high_tension 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 read_high_tension. 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.
read_high_tension 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 →