Read and extract text content from a PubMed paper. Args: paper_id: PubMed ID (PMID). save_path: Directory where the PDF would be saved (unused). Returns: str: Message indicating that direct paper reading is not supported.
AI agents call read_pubmed_paper to retrieve information from Paper Search MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool is designed to retrieve and extract text from academic papers—a read-only operation with no data modification, deletion, or execution capabilities. Even though the current implementation may not fully support the operation, the tool's design intent is purely informational retrieval from PubMed, which is a public academic database.
From the tool's definition Tool name is 'read_pubmed_paper' and description states it 'Read and extract text content from a PubMed paper.' The actual return indicates 'direct paper reading is not supported' but the intended operation is retrieval/extraction of paper content with no…
Documented attack patterns abuse exactly the kind of access read_pubmed_paper gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Paper Search MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for read_pubmed_paper:
{
"version": "1",
"default": "deny",
"tools": {
"read_pubmed_paper": {}
}
}read_pubmed_paper 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.
Read and extract text content from a PubMed paper. Args: paper_id: PubMed ID (PMID). save_path: Directory where the PDF would be saved (unused). Returns: str: Message indicating that direct paper reading is not supported. It is categorised as a Read tool in the Paper Search MCP MCP Server, which means it retrieves data without modifying state.
Register the Paper Search MCP server in PolicyLayer and add a rule for read_pubmed_paper: 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 Paper Search MCP. Nothing to install.
read_pubmed_paper 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 read_pubmed_paper 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 read_pubmed_paper. 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.
read_pubmed_paper is provided by the Paper Search MCP server (openags/paper-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 63 Paper Search MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
63 Paper Search MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.