AI agents use cache_create to create or update resources in Crossref Local — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Crossref Local environment.
The tool creates cache entries, which is a reversible modification operation. While the description is empty, the naming convention and server context (a local academic database) suggest it stores or caches query results or derived data. This is Write-level (modifies state reversibly) rather than Read (query-only) or Destructive (no deletion indicated).
From the tool's definition Tool name 'cache_create' indicates creation of cache entries. The server description mentions 'full-text search across 167M+ scholarly works' and other data retrieval/analysis operations.
Documented attack patterns abuse exactly the kind of access cache_create 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_create:
{
"version": "1",
"default": "deny",
"tools": {
"cache_create": {
"limits": [
{
"counter": "cache_create_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}cache_create stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
cache_create. It is categorised as a Write tool in the Crossref Local MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Crossref Local MCP server in PolicyLayer and add a rule for cache_create: 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_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the cache_create 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_create. 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_create 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.