Searching for academic papers using Google Scholar
AI agents call search_scholar_papers to retrieve information from McpDeepResearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries Google Scholar for academic papers and returns results. It retrieves data with no side effects—it does not create, modify, delete, execute code, or commit financial transactions. The operation is a simple search query against an external academic database, making it a Read category tool with low severity due to minimal risk of misuse.
From the tool's definition Tool description states it enables 'searching Google Scholar' and the sibling tools are 'fetch_md' and 'fetch_paper', indicating this server retrieves academic content without modification. The tool name contains 'search' which is a read operation.
Attacks that exploit this kind of access
Searching for academic papers using Google Scholar. It is categorised as a Read tool in the McpDeepResearch MCP Server, which means it retrieves data without modifying state.
Register the McpDeepResearch MCP server in PolicyLayer and add a rule for search_scholar_papers: 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 McpDeepResearch. Nothing to install.
search_scholar_papers 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_scholar_papers 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_scholar_papers. 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_scholar_papers is provided by the McpDeepResearch MCP server (pb-207/mcp-deep-research). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →