Run an AMQL metrics query against Anypoint Observability. Returns a Chart.js visualization of the time series data alongside raw results. Call metrics_list_types first to discover valid metric names.
AI agents call metrics_search to retrieve information from Anypoint MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Although the tool executes a query (AMQL), the execution is read-only and returns observability/metrics data with no side effects. It does not create, modify, delete, or execute external operations; it retrieves and visualizes existing monitoring data.
From the tool's definition The tool 'metrics_search' runs an AMQL metrics query and 'Returns a Chart.js visualization of the time series data alongside raw results.' This is fundamentally a read operation that retrieves observability metrics without modifying or deleting data.
Attacks that exploit this kind of access
Run an AMQL metrics query against Anypoint Observability. Returns a Chart.js visualization of the time series data alongside raw results. Call metrics_list_types first to discover valid metric names. It is categorised as a Read tool in the Anypoint MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Anypoint MCP Server MCP server in PolicyLayer and add a rule for metrics_search: 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 Anypoint MCP Server. Nothing to install.
metrics_search 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 metrics_search 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 metrics_search. 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.
metrics_search is provided by the Anypoint MCP Server MCP server (sravannerella/mulesoft-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 →