Search Entrez databases with text queries to find matching UIDs. Core Entrez function that converts queries into UID lists for use with other E-utilities. Supports Boolean operators (AND, OR, NOT) and field-specific searches.\n\n🔍 Common PubMed Fields: [Title], [Author], [Journal], [MeSH], [Abst...
AI agents call esearch 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 performs read-only queries against NCBI Entrez databases to retrieve identifiers (UIDs) matching biomedical search criteria. It has no side effects—it does not create, modify, delete, or execute external operations. It is a classic search/retrieval function with no blast radius if misused by an AI agent beyond potentially returning unexpected results or consuming API quota.
From the tool's definition Tool name is 'esearch' and description states it 'Search Entrez databases with text queries to find matching UIDs' and 'converts queries into UID lists'. The function is explicitly a search operation that retrieves data without modifying or deleting anything.
Attacks that exploit this kind of access
Search Entrez databases with text queries to find matching UIDs. Core Entrez function that converts queries into UID lists for use with other E-utilities. Supports Boolean operators (AND, OR, NOT) and field-specific searches.\n\n🔍 Common PubMed Fields: [Title], [Author], [Journal], [MeSH], [Abstract], [Date], [DOI]\n🧬 Sequence DB Fields: [Organism], [Gene], [Protein], [Accession]\n🔬 Search Examples: \n•. 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 esearch: 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.
esearch 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 esearch 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 esearch. 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.
esearch 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 →