AI agents call get_author_info to retrieve information from Google-Scholar-MCP-Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to retrieve author metadata from Google Scholar, which is a read-only operation with no side effects. Google Scholar data is public, so unauthorized access carries minimal blast radius. Confidence is moderately reduced due to empty description, but the naming pattern and server context strongly suggest information retrieval.
From the tool's definition Tool name 'get_author_info' combined with server purpose of accessing Google Scholar data suggests retrieval of publicly available author information. No description provided, limiting certainty.
Documented attack patterns abuse exactly the kind of access get_author_info gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google-Scholar-MCP-Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_author_info:
{
"version": "1",
"default": "deny",
"tools": {
"get_author_info": {}
}
}get_author_info 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_author_info. It is categorised as a Read tool in the Google-Scholar-MCP-Server MCP Server, which means it retrieves data without modifying state.
Register the Google-Scholar-MCP-Server MCP server in PolicyLayer and add a rule for get_author_info: 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 Google-Scholar-MCP-Server. Nothing to install.
get_author_info 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_author_info 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_author_info. 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_author_info is provided by the Google-Scholar-MCP-Server MCP server (jackkuo666/google-scholar-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google-Scholar-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.
3 Google-Scholar-MCP-Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.