AI agents call handoff to retrieve information from Engram without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'handoff' tool reads and compiles existing data (project bundle, sessions, assertions, tensions) into a portable format for transfer between agents. No data is created, modified, deleted, or destroyed in the process—it is purely a data aggregation and serialization operation. This is characteristic of a Read category tool.
From the tool's definition Tool description states it 'Packs project bundle, recent sessions, ledger assertions, and unresolved tensions into a token budget' for handoff purposes.
Attacks that exploit this kind of access
Generate a portable context blob for agent-to-agent handoff. Packs project bundle, recent sessions, ledger assertions, and unresolved tensions into a token budget. It is categorised as a Read tool in the Engram MCP Server, which means it retrieves data without modifying state.
Register the Engram MCP server in PolicyLayer and add a rule for 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 Engram. Nothing to install.
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 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 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.
handoff is provided by the Engram MCP server (tinydarkforge/engram). 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 →