Generate a conservative safe task-management plan from a local backup. This never writes to Microsoft To Do.
AI agents call propose_plan to retrieve information from Microsoft Todo Safe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads from a local backup and generates a plan without making any modifications. The description explicitly states it never writes to Microsoft To Do, making this a pure read/analysis operation with no side effects.
From the tool's definition 'Generate a conservative safe task-management plan from a local backup. This never writes to Microsoft To Do.'
Attacks that exploit this kind of access
Generate a conservative safe task-management plan from a local backup. This never writes to Microsoft To Do. It is categorised as a Read tool in the Microsoft Todo Safe MCP Server, which means it retrieves data without modifying state.
Register the Microsoft Todo Safe MCP server in PolicyLayer and add a rule for propose_plan: 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 Microsoft Todo Safe. Nothing to install.
propose_plan 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 propose_plan 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 propose_plan. 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.
propose_plan is provided by the Microsoft Todo Safe MCP server (saenai/microsoft-todo-safe-mcp). 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 →