AI agents call search_works 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.
This tool retrieves bibliographic records from a scholarly database without modifying, deleting, or executing arbitrary code. The empty description reduces confidence slightly, but the clear Read semantics of 'search' combined with the server's stated search functionality makes this classification high-confidence. No destructive, financial, or code execution capabilities are evident.
From the tool's definition Tool name 'search_works' combined with server description stating it enables 'full-text search across 167M+ scholarly works' indicates a retrieval operation. The suffix 'search' is a canonical Read operation (querying/retrieving data with no side effects).
Documented attack patterns abuse exactly the kind of access search_works 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 search_works:
{
"version": "1",
"default": "deny",
"tools": {
"search_works": {}
}
}search_works 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.
search_works. 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 search_works: 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.
search_works 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 search_works 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 search_works. 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.
search_works 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.