Search for papers in PubMed using a query string and return normalized results.
AI agents call search_pubmed_papers to retrieve information from UniArticles 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 academic literature metadata from PubMed without side effects. It performs a search query and returns results in normalized format. No data is created, modified, deleted, or executed—only queried. This fits the Read category (search, fetch).
From the tool's definition Tool name 'search_pubmed_papers' and description 'Search for papers in PubMed using a query string and return normalized results' indicate a retrieval operation with no modification, deletion, or execution capability.
Documented attack patterns abuse exactly the kind of access search_pubmed_papers gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and UniArticles MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_pubmed_papers:
{
"version": "1",
"default": "deny",
"tools": {
"search_pubmed_papers": {}
}
}search_pubmed_papers 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.
Search for papers in PubMed using a query string and return normalized results. It is categorised as a Read tool in the UniArticles MCP Server MCP Server, which means it retrieves data without modifying state.
Register the UniArticles MCP Server MCP server in PolicyLayer and add a rule for search_pubmed_papers: 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 UniArticles MCP Server. Nothing to install.
search_pubmed_papers 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_papers 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_papers. 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_papers is provided by the UniArticles MCP Server MCP server (thinktraveller/uniarticles_mcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from UniArticles MCP Server, 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.
15 UniArticles MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.