Search handoffs by tags, text query, project, AI, status, or date range. Returns matching handoff summaries without full conversation content. Use this to discover relevant handoffs in multi-agent workflows.
AI agents call handoff_search to retrieve information from Conversation Handoff MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though handoff_search only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
Search handoffs by tags, text query, project, AI, status, or date range. Returns matching handoff summaries without full conversation content. Use this to discover relevant handoffs in multi-agent workflows. It is categorised as a Read tool in the Conversation Handoff MCP MCP Server, which means it retrieves data without modifying state.
Register the Conversation Handoff MCP server in PolicyLayer and add a rule for handoff_search: 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_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the handoff_search 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_search. 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_search 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.