Restart the shared HTTP server. Useful when the server is in an unhealthy state. All stored handoffs will be lost (data is in-memory).
AI agents invoke handoff_restart to trigger actions in Conversation Handoff MCP. 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.
handoff_restart triggers real processes with real consequences. An agent gone sideways doesn't fire it once — it starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
Restart the shared HTTP server. Useful when the server is in an unhealthy state. All stored handoffs will be lost (data is in-memory). It is categorised as a Execute tool in the Conversation Handoff MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Conversation Handoff MCP server in PolicyLayer and add a rule for handoff_restart: 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 Conversation Handoff MCP. Nothing to install.
handoff_restart 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 handoff_restart 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 handoff_restart. 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.
handoff_restart is provided by the Conversation Handoff MCP server (trust-delta/conversation-handoff-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.