Fetch full-text articles from PubMed Central with structured sections and references. When PMC misses, transparently falls back to Europe PMC fullTextXML (structured JATS for records with a PMC counterpart), then to Unpaywall — publisher-hosted or institutional open-access copies as HTML-as-Markd...
Part of the Pubmed server.
Free to start. No card required.
AI agents call pubmed_fetch_fulltext to retrieve information from Pubmed without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though pubmed_fetch_fulltext only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"pubmed_fetch_fulltext": {}
}
} See the full Pubmed policy for all 10 tools.
These attack patterns abuse exactly the kind of access pubmed_fetch_fulltext gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Fetch full-text articles from PubMed Central with structured sections and references. When PMC misses, transparently falls back to Europe PMC fullTextXML (structured JATS for records with a PMC counterpart), then to Unpaywall — publisher-hosted or institutional open-access copies as HTML-as-Markdown or PDF-as-text. Provide exactly one of pmcids (PMC IDs directly), pmids (PubMed IDs, auto-resolved), or dois (DOIs, auto-resolved to PMC via the ID Converter; preprints and EPMC-only OA fall through to the Europe PMC and Unpaywall layers).. It is categorised as a Read tool in the Pubmed MCP Server, which means it retrieves data without modifying state.
Register the Pubmed MCP server in PolicyLayer and add a rule for pubmed_fetch_fulltext: 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. Nothing to install.
pubmed_fetch_fulltext 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 pubmed_fetch_fulltext 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 pubmed_fetch_fulltext. 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.
pubmed_fetch_fulltext is provided by the Pubmed MCP server (@cyanheads/pubmed-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 10 Pubmed tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.