AI agents invoke governance_kill_switch to trigger actions in VibeServe. 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 halts all agent operations system-wide, acting as an emergency stop. It triggers a broad operational change (disabling all agent activity) rather than deleting data, making Execute the best fit. However, the blast radius is critical: misuse by an AI agent would immediately and globally disable all agentic pipeline operations on the server, causing severe disruption to all ongoing work.
From the tool's definition Kill switch — disable all Big-Homie agent operations
Attacks that exploit this kind of access
Kill switch — disable all Big-Homie agent operations. It is categorised as a Execute tool in the VibeServe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VibeServe MCP server in PolicyLayer and add a rule for governance_kill_switch: 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 VibeServe. Nothing to install.
governance_kill_switch 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 governance_kill_switch 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 governance_kill_switch. 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.
governance_kill_switch is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →