Save a conversation handoff for later retrieval. Use this to pass conversation context to another AI or project. Long conversations (>~100KB) If the conversation is large, save the first chunk with this tool, then call \
AI agents use handoff_save to create or update resources in Conversation Handoff MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Conversation Handoff MCP environment.
An AI agent can call handoff_save faster than any human can review — one bad instruction and it creates or modifies resources in Conversation Handoff MCP by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
Save a conversation handoff for later retrieval. Use this to pass conversation context to another AI or project. Long conversations (>~100KB) If the conversation is large, save the first chunk with this tool, then call \. It is categorised as a Write tool in the Conversation Handoff MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Conversation Handoff MCP server in PolicyLayer and add a rule for handoff_save: 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_save is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the handoff_save 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_save. 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_save 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.