AI agents use create_retrospective 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 generates new analytical/report documents from existing completed project data. It transforms and synthesizes information into a new artifact (the retrospective report) but does not modify existing task data, delete anything, execute code, or move money. The action is reversible (the report can be discarded) and produces no side effects beyond creating the report file.
From the tool's definition Tool creates a retrospective report from project data (plans, estimates, blockers, verifications). The verb 'Create' and the action of generating a new report document indicates data creation.
Attacks that exploit this kind of access
Create a local retrospective report for a project or plan from completed plans, missed estimates, recurring blockers, failed verifications, and suggested follow-up tasks. 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_retrospective: 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_retrospective 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_retrospective 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_retrospective. 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_retrospective 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 →