Search PubMed for systematic reviews and meta-analyses only.
AI agents call find_reviews to retrieve information from Pubmed Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches and retrieves data from PubMed's public database. It is purely informational with no capability to modify data, execute external operations, delete records, or commit financial transactions. The most severe risk is information retrieval, making this a Read category tool with low severity since PubMed is a public resource and search queries carry minimal blast radius.
From the tool's definition Tool description states 'Search PubMed for systematic reviews and meta-analyses only' — this is a query/search operation that retrieves literature data without modifying, executing code, or having side effects.
Attacks that exploit this kind of access
Search PubMed for systematic reviews and meta-analyses only. It is categorised as a Read tool in the Pubmed Search MCP Server, which means it retrieves data without modifying state.
Register the Pubmed Search MCP server in PolicyLayer and add a rule for find_reviews: 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 Search. Nothing to install.
find_reviews 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 find_reviews 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 find_reviews. 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.
find_reviews is provided by the Pubmed Search MCP server (pubspro/pubmed-search). 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 →