Fetch detailed article information from PubMed using PMIDs.
AI agents call fetch_summary 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 article summaries and metadata from PubMed by PMID (PubMed ID). It performs a read-only query operation with no side effects, no data modification, no code execution, and no financial implications. The low severity reflects that misuse would only expose publicly available scientific literature information.
From the tool's definition 'Fetch detailed article information from PubMed using PMIDs' - describes retrieving/querying existing article metadata and summaries without modification or execution of external operations.
Attacks that exploit this kind of access
Fetch detailed article information from PubMed using PMIDs. 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 fetch_summary: 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.
fetch_summary 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 fetch_summary 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 fetch_summary. 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.
fetch_summary 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 →