AI agents call cache_info to retrieve information from OpenAPI Directory MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries cache configuration information without creating, modifying, deleting, or executing any operations. It is a pure read operation on cache state, making it low severity with minimal blast radius even if misused by an AI agent.
From the tool's definition Tool name 'cache_info' and description 'Get cache configuration and settings' indicate retrieval of existing cache metadata with no modification or side effects.
Documented attack patterns abuse exactly the kind of access cache_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OpenAPI Directory MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_info:
{
"version": "1",
"default": "deny",
"tools": {
"cache_info": {}
}
}cache_info is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get cache configuration and settings. It is categorised as a Read tool in the OpenAPI Directory MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenAPI Directory MCP Server MCP server in PolicyLayer and add a rule for cache_info: 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 OpenAPI Directory MCP Server. Nothing to install.
cache_info 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 cache_info 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_info. 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_info is provided by the OpenAPI Directory MCP Server MCP server (rawveg/openapi-directory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OpenAPI Directory MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
22 OpenAPI Directory MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.