AI agents invoke set_led to trigger actions in Tractive. 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.
This tool triggers an external operation on a physical device (the GPS tracker), turning its LED on or off. It doesn't merely read data, nor does it write data reversibly in a software sense — it actuates hardware. This classifies as Execute since it triggers an external operation on a real-world device. Misuse could drain battery or signal the pet's presence/absence, but the blast radius is limited.
From the tool's definition Turn the tracker LED light on or off
Attacks that exploit this kind of access
Turn the tracker LED light on or off. It is categorised as a Execute tool in the Tractive MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Tractive MCP server in PolicyLayer and add a rule for set_led: 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 Tractive. Nothing to install.
set_led 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_led 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_led. 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_led is provided by the Tractive MCP server (rexchoppers/tractive-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 →