AI agents call staleness to retrieve information from Tages without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a diagnostic/audit tool that examines metadata about existing memories to determine their relevance status. It performs a read-only check with no side effects on the data it inspects. The action is non-destructive (does not delete), non-modifying (does not update), and does not execute code or trigger external operations.
From the tool's definition Tool name 'staleness' and description 'Check for stale memories that may be outdated or no longer relevant' indicate a query or inspection operation that retrieves and evaluates the status of stored memories without modifying, deleting, or executing external…
Attacks that exploit this kind of access
Check for stale memories that may be outdated or no longer relevant. It is categorised as a Read tool in the Tages MCP Server, which means it retrieves data without modifying state.
Register the Tages MCP server in PolicyLayer and add a rule for staleness: 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 Tages. Nothing to install.
staleness 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 staleness 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 staleness. 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.
staleness is provided by the Tages MCP server (ryantlee25-droid/tages). 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 →