AI agents call cache_query to retrieve information from Crossref Local without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the naming pattern ('cache_*') and context (local scholarly database, citation analysis) strongly indicate this queries cached metadata. No evidence of write, delete, code execution, or financial operations. The tool operates on a read-only local database snapshot. Lower confidence due to missing description, but category and severity are well-supported by server context.
From the tool's definition Tool name 'cache_query' with 'query' verb suggests data retrieval. Sibling tools like 'cache_list', 'cache_stats', 'cache_top_cited' indicate read-only operations over cached scholarly data.
Documented attack patterns abuse exactly the kind of access cache_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crossref Local, and nothing reaches the server without passing your rules. This is the rule we recommend for cache_query:
{
"version": "1",
"default": "deny",
"tools": {
"cache_query": {}
}
}cache_query 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.
cache_query. It is categorised as a Read tool in the Crossref Local MCP Server, which means it retrieves data without modifying state.
Register the Crossref Local MCP server in PolicyLayer and add a rule for cache_query: 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 Crossref Local. Nothing to install.
cache_query 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_query 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_query. 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_query is provided by the Crossref Local MCP server (ywatanabe1989/crossref-local). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crossref Local, 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.
17 Crossref Local tools catalogued and risk-classified — across an index of 43,000+ MCP servers.