Fetch ALL terms for ALL taxonomies and cache them in SQLite. Should be run before a full export for fast term lookups.
AI agents call cache_terms to retrieve information from WP Astro MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool fetches data from WordPress taxonomies via REST API and stores it locally in a SQLite cache. This is a read/query operation with a local write side-effect (caching), but the caching is a performance optimization with no external destructive or financial implications. The primary action is data retrieval; local cache writes are reversible and low-risk.
From the tool's definition Fetch ALL terms for ALL taxonomies and cache them in SQLite. Should be run before a full export for fast term lookups.
Documented attack patterns abuse exactly the kind of access cache_terms gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and WP Astro MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_terms:
{
"version": "1",
"default": "deny",
"tools": {
"cache_terms": {}
}
} cache_terms 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.
Fetch ALL terms for ALL taxonomies and cache them in SQLite. Should be run before a full export for fast term lookups. It is categorised as a Read tool in the WP Astro MCP MCP Server, which means it retrieves data without modifying state.
Register the WP Astro MCP server in PolicyLayer and add a rule for cache_terms: 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 WP Astro MCP. Nothing to install.
cache_terms 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_terms 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_terms. 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_terms is provided by the WP Astro MCP server (vapvarun/wp-astro-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from WP Astro MCP, 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.
60 WP Astro MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.