Get papers by author.
AI agents call get_author_papers to retrieve information from Scholar Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves a list of papers associated with an author—a pure query operation with no side effects. It matches the 'Read' category definition: retrieves or queries data without side effects. The severity is low because misuse would only expose academic metadata already public in scholarly databases, with no destructive or financial impact.
From the tool's definition Tool name 'get_author_papers' and description 'Get papers by author' indicate data retrieval with no modification, deletion, or execution. The server's stated purpose is to 'search and retrieve academic paper metadata,' confirming read-only operations.
Attacks that exploit this kind of access
Get papers by author. It is categorised as a Read tool in the Scholar Search MCP Server, which means it retrieves data without modifying state.
Register the Scholar Search MCP server in PolicyLayer and add a rule for get_author_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 Scholar Search. Nothing to install.
get_author_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 get_author_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 get_author_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.
get_author_papers is provided by the Scholar Search MCP server (silung/scholar-search-mcp). 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 →