AI agents call ESearch to retrieve information from Ncbi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
ESearch is a read-only operation that queries NCBI databases (PubMed, Protein, Nucleotide, etc.) and returns matching record identifiers. It has no side effects, cannot modify or delete data, and does not execute arbitrary code. The actual data retrieval is deferred to other tools (EFetch, ESummary). This fits the 'Read' category as a search/query operation with minimal risk.
From the tool's definition Tool description states it 'returns IDs' and 'further retrieval requires calling other tools', indicating it performs search queries without modifying data. The term 'ESearch' and context of NCBI E-utilities API confirm this is a search operation.
Attacks that exploit this kind of access
term为要查询项，db为要查询的库，如不提供db，则默认在pubmed库中查找。返回结果为所在库的id，进一步获取需调用其他tool。. It is categorised as a Read tool in the Ncbi MCP Server, which means it retrieves data without modifying state.
Register the Ncbi 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 Ncbi. 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 Ncbi MCP server (qigoki/ncbi-mcp). 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 →