Check whether the NCBI datasets/dataformat CLI tools are installed and,
AI agents call ensure_cli to retrieve information from Ncbi Datasets without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool checks for the presence of CLI tools, which is a read/query operation against the local system state. However, the description is truncated ('and,') which slightly lowers confidence that there are no installation/write side effects. Based on available evidence, this appears to be a read-only check.
From the tool's definition 'Check whether the NCBI datasets/dataformat CLI tools are installed' — a verification/inspection action with no side effects described
Attacks that exploit this kind of access
Check whether the NCBI datasets/dataformat CLI tools are installed and,. It is categorised as a Read tool in the Ncbi Datasets MCP Server, which means it retrieves data without modifying state.
Register the Ncbi Datasets MCP server in PolicyLayer and add a rule for ensure_cli: 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 Datasets. Nothing to install.
ensure_cli 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 ensure_cli 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 ensure_cli. 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.
ensure_cli is provided by the Ncbi Datasets MCP server (syntheticgio/ncbi-datasets-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 →