AI agents use create_roadmap 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 new data objects and stores them locally, which is a reversible write operation. It does not execute external commands, delete data irreversibly, or move money. The 'medium' severity reflects that misuse could clutter task management state or create misleading project structure, but the impact is limited to the local todo system and can be reversed by deletion or modification.
From the tool's definition The tool description states it will 'Create a local roadmap' - the verb 'create' indicates this tool generates and persists new data structures (roadmap, milestones, plans, tasks, runs, release labels).
Attacks that exploit this kind of access
Create a local roadmap for grouping milestones, plans, tasks, runs, and release labels. 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 create_roadmap: 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.
create_roadmap 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 create_roadmap 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 create_roadmap. 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.
create_roadmap 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 →