AI agents invoke cache.refresh to trigger actions in Or Info. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers an external operation — fetching and refreshing data from remote sources (OpenRouter and LMArena) and updating a local cache. It goes beyond a simple read (it modifies the local cache state) and executes an external network operation. It's not purely destructive or financial, but it does trigger side effects (cache invalidation and rewrite), making Execute the most appropriate category.
From the tool's definition Force-refresh the local cache: OpenRouter model catalog + LMArena ELO data
Attacks that exploit this kind of access
Force-refresh the local cache: OpenRouter model catalog + LMArena ELO data. It is categorised as a Execute tool in the Or Info MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Or Info MCP server in PolicyLayer and add a rule for cache.refresh: 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 Or Info. Nothing to install.
cache.refresh is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the cache.refresh 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 cache.refresh. 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.
cache.refresh is provided by the Or Info MCP server (jmtrs/or-info). 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 →