AI agents call passoff_list 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.
passoff_list performs a query/list operation that returns metadata about existing handoffs. It has no side effects, does not execute code, create, modify, or delete data. This is a straightforward read operation with minimal risk—an AI agent could at worst discover what handoffs exist in a project, which is low-impact information retrieval.
From the tool's definition Tool description states 'List recent handoffs in the current project (metadata only, no body)' and is 'Useful for discovery', indicating it retrieves and lists data without modifying or deleting anything.
Attacks that exploit this kind of access
List recent handoffs in the current project (metadata only, no body). Useful for discovery before loading a specific handoff. 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_list: 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_list 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_list 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_list. 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_list 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 →