AI agents call passoff_thread to retrieve information from Passoff without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays provenance information (ancestor/descendant chains) about existing handoffs. It is a read-only query operation with no side effects, no code execution, no data modification or deletion, and no financial impact. The low severity reflects minimal risk if misused by an AI agent.
From the tool's definition Tool name 'passoff_thread' with description 'Show the lineage chain' and 'tracing how a decision evolved' — presents historical data about handoff relationships without modifying, deleting, or executing operations.
Attacks that exploit this kind of access
Show the lineage chain of a handoff — ancestors, descendants, or both. Useful for tracing how a decision evolved across multiple AI agents. It is categorised as a Read tool in the Passoff MCP Server, which means it retrieves data without modifying state.
Register the Passoff MCP server in PolicyLayer and add a rule for passoff_thread: 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 Passoff. Nothing to install.
passoff_thread 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 passoff_thread 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 passoff_thread. 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.
passoff_thread is provided by the Passoff MCP server (themrgu/ai-agent-context-passoff). 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 →