AI agents call format_handoff_packet to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes handoff packet data and reformats it for display/serialization purposes. This is a data transformation operation with no side effects, no external execution, and no modifications to underlying data. It falls clearly into the Read category as it only retrieves and presents information in different formats.
From the tool's definition Tool description states 'Format a handoff packet as JSON or Markdown' - formatting is a read-only operation that transforms existing data into different representations without modifying or executing anything.
Attacks that exploit this kind of access
Format a handoff packet as JSON or Markdown. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for format_handoff_packet: 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 Todos. Nothing to install.
format_handoff_packet 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 format_handoff_packet 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 format_handoff_packet. 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.
format_handoff_packet is provided by the Todos MCP server (@hasna/todos). 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 →