High level drive command.
AI agents invoke drive to trigger actions in KentraBOT MCP Server. 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.
Driving a physical robot is an external operation with real-world consequences. Misuse could cause property damage, injury, or collision. The tool executes movement commands on hardware, placing it firmly in Execute. Severity is high because physical robots operating in uncontrolled environments pose safety risks.
From the tool's definition 'High level drive command' on a server that 'Enables LLMs to control a two-track robot through movement commands' — this triggers physical actuation of a real-world robot.
Attacks that exploit this kind of access
High level drive command. It is categorised as a Execute tool in the KentraBOT MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the KentraBOT MCP Server MCP server in PolicyLayer and add a rule for drive: 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 KentraBOT MCP Server. Nothing to install.
drive 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 drive 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 drive. 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.
drive is provided by the KentraBOT MCP Server MCP server (kentra/kentrabot-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 →