search_analytics
AI agents call search_analytics to retrieve information from EMS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to search or query analytics data from the EMS system based on naming and server context. This is a Read operation (retrieves data with no side effects). Severity is medium rather than low because analytics access on aviation/flight data could have operational impact if misused (e.g., querying sensitive flight information). Confidence is reduced due to empty tool description.
From the tool's definition Tool name 'search_analytics' suggests querying/searching analytical data. Server description confirms tools 'query flight records, retrieve time-series analytics, and explore aircraft assets' with no mention of write/delete capabilities.
Attacks that exploit this kind of access
search_analytics. It is categorised as a Read tool in the EMS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the EMS MCP Server MCP server in PolicyLayer and add a rule for search_analytics: 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 EMS MCP Server. Nothing to install.
search_analytics 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 search_analytics 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 search_analytics. 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.
search_analytics is provided by the EMS MCP Server MCP server (mattsq/ems-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 →