AI agents call find_related_articles 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 appears to query and retrieve related articles from PubMed or similar academic databases based on input articles. This is a classic Read operation—it retrieves data without modifying, deleting, or executing external actions. The low severity reflects minimal blast radius: misuse would return irrelevant search results but cause no harm to data or systems.
From the tool's definition Tool name is 'find_related_articles' which indicates retrieval of related research articles from academic databases. The server is described as providing 'literature search and analysis' across academic databases.
Documented attack patterns abuse exactly the kind of access find_related_articles gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pubmed Search, and nothing reaches the server without passing your rules. This is the rule we recommend for find_related_articles:
{
"version": "1",
"default": "deny",
"tools": {
"find_related_articles": {}
}
}find_related_articles is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
find_related_articles. 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_related_articles: 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_related_articles 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_related_articles 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_related_articles. 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_related_articles is provided by the Pubmed Search MCP server (u9401066/pubmed-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pubmed Search, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
63 Pubmed Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.