preview_retention_cleanup
Preview local retention cleanup candidates for comments, runs, verification evidence, and expired artifact files. Never returns raw evidence content.
This record as markdown: /tools/todos/preview-retention-cleanup.md
What preview_retention_cleanup does on Todos
AI agents call preview_retention_cleanup to retrieve information from Todos without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why preview_retention_cleanup is rated Low
This tool performs inspection/preview of potential cleanup candidates without executing the cleanup itself. It retrieves information about what could be deleted (comments, runs, artifacts) but does not delete, modify, or execute any changes. The explicit statement that it never returns raw evidence content further confirms it is a safe, read-only operation.
From the tool's definition Tool description states it "Preview[s]" cleanup candidates and explicitly specifies "Never returns raw evidence content", indicating a read-only inspection capability with no modification or deletion of actual data.
Attacks that exploit this kind of access
The rule that runs preview_retention_cleanup safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Todos, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For preview_retention_cleanup, this is the rule to start with:
preview_retention_cleanup is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Todos, apply this rule, and every preview_retention_cleanup call is checked against it from then on.
Questions about preview_retention_cleanup
Preview local retention cleanup candidates for comments, runs, verification evidence, and expired artifact files. Never returns raw evidence content. 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 preview_retention_cleanup: 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.
preview_retention_cleanup 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 preview_retention_cleanup 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 preview_retention_cleanup. 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.
preview_retention_cleanup 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.
More on Todos, and thousands of servers like it.
This server
Across the catalogue