Search multiple scholarly metadata providers (OpenAlex, Crossref, Semantic Scholar, optional Scholar scrape) and return canonicalized paper records.
AI agents call search_literature_graph to retrieve information from ScholarMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries academic metadata from multiple sources (OpenAlex, Crossref, Semantic Scholar) and returns canonicalized results. It has no side effects on the queried databases or the user's data. It is purely informational retrieval, fitting the Read category. Severity is low because misuse would at worst return irrelevant search results with no destructive or harmful consequences.
From the tool's definition Tool performs search operations across scholarly metadata providers and returns paper records. The name contains 'search' and description uses 'Search... and return', indicating retrieval without modification.
Documented attack patterns abuse exactly the kind of access search_literature_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ScholarMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_literature_graph:
{
"version": "1",
"default": "deny",
"tools": {
"search_literature_graph": {}
}
} search_literature_graph 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 multiple scholarly metadata providers (OpenAlex, Crossref, Semantic Scholar, optional Scholar scrape) and return canonicalized paper records. It is categorised as a Read tool in the ScholarMCP MCP Server, which means it retrieves data without modifying state.
Register the Scholar MCP server in PolicyLayer and add a rule for search_literature_graph: 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 ScholarMCP. Nothing to install.
search_literature_graph 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_literature_graph 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_literature_graph. 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_literature_graph is provided by the Scholar MCP server (lstudlo/scholarmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ScholarMCP, 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.
10 ScholarMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.