AI agents call export_plan_execution_contract 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.
'Export' implies reading/serializing existing plan data into a JSON format for transfer. No indication of data modification, deletion, financial operations, or code execution. The output is a JSON contract, which is a read-like operation. Confidence is moderate because 'export' could theoretically trigger side effects, but the description suggests it's a data retrieval/serialization operation.
From the tool's definition Export portable plan execution contract JSON for hosted bridge
Attacks that exploit this kind of access
Export portable plan execution contract JSON for hosted bridge. 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 export_plan_execution_contract: 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.
export_plan_execution_contract 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 export_plan_execution_contract 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 export_plan_execution_contract. 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.
export_plan_execution_contract 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 →