Assemble a source-backed handoff pack for one namespace: current state, recent decisions, open loops, recent actors, and recommended next actions. Use this when one agent or environment is handing work to another.\n\nIf this is your first memory operation in this conversation, call memory_orient ...
AI agents call memory_handoff to retrieve information from Munin Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
memory_handoff queries and assembles existing memory data for transfer between agents without modifying, deleting, or executing code. While the severity is medium (not low) because it handles potentially sensitive session context that could be misused if accessed by a malicious agent, the operation itself is read-only.
From the tool's definition Tool description states it 'Assemble[s]' and retrieves information ('current state, recent decisions, open loops, recent actors, and recommended next actions'). No modification, deletion, or execution of external operations is described.
Attacks that exploit this kind of access
Assemble a source-backed handoff pack for one namespace: current state, recent decisions, open loops, recent actors, and recommended next actions. Use this when one agent or environment is handing work to another.\n\nIf this is your first memory operation in this conversation, call memory_orient first. It is categorised as a Read tool in the Munin Memory MCP Server, which means it retrieves data without modifying state.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_handoff: 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 Munin Memory. Nothing to install.
memory_handoff 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 memory_handoff 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 memory_handoff. 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.
memory_handoff is provided by the Munin Memory MCP server (magnus-gille/munin-memory). 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 →