AI agents call format_goal_handoff 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.
This tool generates formatted output from existing data without creating, modifying, deleting, or executing operations. It is a retrieval and formatting operation with no side effects on the task management system. The sibling tools show write operations like add_*, execute operations like add_task_run_command, and state-changes like acquire_task_lease, but this tool is purely a presentational formatter.
From the tool's definition Tool produces/renders output ('Produce JSON or Markdown handoff packet') without modifying underlying task data. The action is to format and return a representation of an existing /goal plan.
Attacks that exploit this kind of access
Produce JSON or Markdown handoff packet for a /goal plan. 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_goal_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 Todos. Nothing to install.
format_goal_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 format_goal_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 format_goal_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.
format_goal_handoff 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 →