AI agents use attach_plan_to_project to create or update resources in Todos — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Todos environment.
This tool creates or modifies data by establishing a relationship between a plan and a project, and initializing execution mode. These are reversible structural changes to task management data. It does not delete data (not Destructive), execute arbitrary code (not Execute), involve financial operations (not Financial), or merely read data (not Read).
From the tool's definition Tool description states 'Attach a plan to a project and initialize plan execution mode.' The word 'attach' and 'initialize' indicate creation/modification of project state relationships.
Attacks that exploit this kind of access
Attach a plan to a project and initialize plan execution mode. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Todos MCP server in PolicyLayer and add a rule for attach_plan_to_project: 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.
attach_plan_to_project is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the attach_plan_to_project 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 attach_plan_to_project. 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.
attach_plan_to_project 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 →