Search PubMed for scientific articles.
AI agents call search_pubmed to retrieve information from PubMed MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves scientific article metadata from PubMed. It has no side effects, does not modify data, execute code, delete content, or move money. The operation is purely informational and reversible. Rate limiting and caching mentioned in the server description are protective measures that do not change the classification.
From the tool's definition Tool name 'search_pubmed' and description 'Search PubMed for scientific articles' indicate a query operation that retrieves data from PubMed without modification.
Attacks that exploit this kind of access
Search PubMed for scientific articles. It is categorised as a Read tool in the PubMed MCP Server MCP Server, which means it retrieves data without modifying state.
Register the PubMed MCP Server 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 PubMed MCP Server. 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 PubMed MCP Server MCP server (ncukondo/pubmed-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 →