AI agents call get_work_metadata to retrieve information from Crossref MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about academic works from Crossref without modifying, executing operations, or accessing restricted content. It is a pure read operation with no side effects. The empty description slightly reduces confidence, but the clear context from the server description and naming convention strongly indicate metadata retrieval functionality.
From the tool's definition Tool name 'get_work_metadata' combined with server description stating it 'retrieve[s] detailed metadata for papers, journals, and funding organizations via the Crossref database' and 'DOI-based lookups' indicates a retrieval operation.
Documented attack patterns abuse exactly the kind of access get_work_metadata gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crossref MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_work_metadata:
{
"version": "1",
"default": "deny",
"tools": {
"get_work_metadata": {}
}
} get_work_metadata 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_work_metadata. It is categorised as a Read tool in the Crossref MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Crossref MCP Server MCP server in PolicyLayer and add a rule for get_work_metadata: 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 MCP Server. Nothing to install.
get_work_metadata 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 get_work_metadata 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 get_work_metadata. 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.
get_work_metadata is provided by the Crossref MCP Server MCP server (jackkuo666/crossref-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crossref 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.
9 Crossref MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.