Force refresh the model cache from OpenRouter.
AI agents invoke refresh_cache to trigger actions in OpenRouter MCP Server. 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 updated data from OpenRouter and refreshing a local cache). It has side effects beyond a simple read, but does not permanently delete data or move money. It fits Execute as it triggers an external fetch/update operation whose effects depend on the current state of the remote API.
From the tool's definition Force refresh the model cache from OpenRouter
Attacks that exploit this kind of access
Force refresh the model cache from OpenRouter. It is categorised as a Execute tool in the OpenRouter MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OpenRouter MCP Server 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 OpenRouter MCP Server. Nothing to install.
refresh_cache 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 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 OpenRouter MCP Server MCP server (lumishoang/openrouter-mcp). 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 →