Search PubMed for medical literature
AI agents call search-pubmed to retrieve information from Agent Care MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a public medical literature database (PubMed) and returns search results. It retrieves information without side effects, creating no data, executing no code, modifying no records, and incurring no financial obligations. While the broader server handles sensitive patient data via FHIR, this specific tool operates on open scientific literature and poses minimal security risk.
From the tool's definition Tool name 'search-pubmed' and description 'Search PubMed for medical literature' indicate retrieval of publicly available medical research data with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Search PubMed for medical literature. It is categorised as a Read tool in the Agent Care MCP MCP Server, which means it retrieves data without modifying state.
Register the Agent Care 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 Agent Care 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 Agent Care MCP server (polya20/agentcare-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 →