AI agents use manage_cache to create or update resources in Asterdex — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Asterdex environment.
Cache management is inherently a Write operation—it modifies local data storage reversibly. While the specific capabilities are not fully detailed, the description indicates interaction with a cache system, which typically allows create, update, and clear operations. Severity is low because cache corruption or loss affects performance and data freshness but not critical business logic or permanent data loss.
From the tool's definition Tool name 'manage_cache' and description 'Interact with the local data cache' indicate operations that create, modify, or clear cached data.
Attacks that exploit this kind of access
Interact with the local data cache. It is categorised as a Write tool in the Asterdex MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Asterdex MCP server in PolicyLayer and add a rule for manage_cache: 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 Asterdex. Nothing to install.
manage_cache 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 manage_cache 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 manage_cache. 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.
manage_cache is provided by the Asterdex MCP server (tyranosurasmax/asterdex-mcp-server). 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 →