Search academic papers from PubMed. Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). sort: Sort order — 'relevance' or 'pub_date' (default: 'relevance'). Returns: List of paper metadata in dictionary format.
AI agents call search_pubmed to retrieve information from Paper Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and queries publicly available academic paper metadata from PubMed. It performs a passive search operation with no capability to create, modify, delete, or execute code. The return of metadata constitutes a read-only operation with no adverse consequences from misuse beyond potentially excessive query volume.
From the tool's definition Tool description explicitly states it 'Search[es] academic papers' and 'Returns: List of paper metadata' with no ability to modify, delete, or execute operations. Parameters are limited to search criteria (query, max_results, sort) with no side effects.
Documented attack patterns abuse exactly the kind of access search_pubmed gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Paper Search MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_pubmed:
{
"version": "1",
"default": "deny",
"tools": {
"search_pubmed": {}
}
}search_pubmed 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.
Search academic papers from PubMed. Args: query: Search query string (e.g., 'machine learning'). max_results: Maximum number of papers to return (default: 10). sort: Sort order — 'relevance' or 'pub_date' (default: 'relevance'). Returns: List of paper metadata in dictionary format. It is categorised as a Read tool in the Paper Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Paper Search MCP server in PolicyLayer and add a rule for search_pubmed: 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 MCP. Nothing to install.
search_pubmed 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_pubmed 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_pubmed. 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_pubmed is provided by the Paper Search MCP server (openags/paper-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 63 Paper Search MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
63 Paper Search MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.