Access PubChem chemistry and PMC article utilities from one entry point.
AI agents call entrez-external to retrieve information from Entrez 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 or queries data from public biomedical databases (PubChem and PMC). These are read-only operations with no side effects, no code execution, and no data modification. The blast_submit sibling suggests some tools on this server may trigger operations, but this specific tool appears to be a retrieval/access endpoint.
From the tool's definition Tool name 'entrez-external' and description indicate access to PubChem chemistry data and PMC article utilities, which are query/retrieval operations.
Attacks that exploit this kind of access
Access PubChem chemistry and PMC article utilities from one entry point. It is categorised as a Read tool in the Entrez MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Entrez MCP Server MCP server in PolicyLayer and add a rule for entrez-external: 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 Entrez MCP Server. Nothing to install.
entrez-external 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 entrez-external 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 entrez-external. 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.
entrez-external is provided by the Entrez MCP Server MCP server (leongxj123/entrez-mcp-server). 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 →