Retrieve full abstract for a given PubMed ID (PMID).
AI agents call get_abstract 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.
This tool queries PubMed to fetch pre-existing abstract text. It performs no writes, deletions, code execution, or financial transactions. The operation is a simple data retrieval with no capability to modify or destroy information. Low severity because abstracting academic literature is a benign research activity with negligible risk of misuse.
From the tool's definition Tool description states 'Retrieve full abstract for a given PubMed ID (PMID)' - the verb 'retrieve' indicates a read-only operation with no side effects.
Attacks that exploit this kind of access
Retrieve full abstract for a given PubMed ID (PMID). 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 get_abstract: 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.
get_abstract 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 get_abstract 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 get_abstract. 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.
get_abstract 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 →