AI agents call scholar_search to retrieve information from Mcp Scholar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to search a scholarly database and retrieve papers based on queries. No side effects are described or implied; it does not modify, delete, or execute external operations. It is purely a read operation. Severity is low because misuse yields only information disclosure of publicly available academic content, with minimal blast radius.
From the tool's definition Tool name 'scholar_search' within a Google Scholar search server, sibling tools include 'adaptive_search', 'paper_detail', 'paper_references', 'profile_papers', and 'summarize_papers'—all data retrieval operations.
Documented attack patterns abuse exactly the kind of access scholar_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Scholar, and nothing reaches the server without passing your rules. This is the rule we recommend for scholar_search:
{
"version": "1",
"default": "deny",
"tools": {
"scholar_search": {}
}
}scholar_search 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.
scholar_search. It is categorised as a Read tool in the Mcp Scholar MCP Server, which means it retrieves data without modifying state.
Register the Mcp Scholar MCP server in PolicyLayer and add a rule for scholar_search: 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 Mcp Scholar. Nothing to install.
scholar_search 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 scholar_search 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 scholar_search. 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.
scholar_search is provided by the Mcp Scholar MCP server (renyumeng1/mcp_scholar). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 7 Mcp Scholar tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
7 Mcp Scholar tools catalogued and risk-classified — across an index of 42,500+ MCP servers.