Look up a single paper by identifier. Auto-detects ID type and queries the right platform(s)
AI agents call get_paper to retrieve information from Paper Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves academic paper metadata by identifier lookup across scholarly databases (Semantic Scholar, arXiv, PubMed, CrossRef). It is a read-only query operation that returns information without side effects. Even if an AI agent misuses it by looking up many papers, the blast radius is negligible — at worst, it generates queries against public research APIs.
From the tool's definition Tool description states 'Look up a single paper by identifier' and 'queries the right platform(s)' — purely retrieval operations with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Look up a single paper by identifier. Auto-detects ID type and queries the right platform(s). It is categorised as a Read tool in the Paper Search MCP Server, which means it retrieves data without modifying state.
Register the Paper Search MCP server in PolicyLayer and add a rule for get_paper: 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 Paper Search. Nothing to install.
get_paper 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_paper 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_paper. 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_paper is provided by the Paper Search MCP server (upascal/paper-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 →