AI agents use refresh_cache to create or update resources in Mcp Proxy — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Proxy environment.
This tool modifies the cached tool definitions stored by the proxy server. While it does not delete or irreversibly destroy data (precluding Destructive), and it does not create new entries in a persistent system (Write rather than Execute), it does alter the state of the cache.
From the tool's definition The tool performs 'Force re-fetch' and 'update cache', which are write operations that modify cached state. The description uses language indicating mutation of the local cache state.
Attacks that exploit this kind of access
Force re-fetch tool definitions from a server (or all servers) and update cache. It is categorised as a Write tool in the Mcp Proxy MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Proxy MCP server in PolicyLayer and add a rule for refresh_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 Mcp Proxy. Nothing to install.
refresh_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 refresh_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 refresh_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.
refresh_cache is provided by the Mcp Proxy MCP server (shengxiao20/mcp-proxy-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 →