Retrieve operational metrics from the Tensorus service.
AI agents call management_get_metrics to retrieve information from Tensorus MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves monitoring/observability data from the service without creating, modifying, deleting, or executing any operations. It has no blast radius if misused by an agent—at worst, an agent could learn system performance details, which poses minimal security risk. The read-only nature and informational scope justify the 'Read' category with low severity.
From the tool's definition Tool name 'management_get_metrics' with description 'Retrieve operational metrics from the Tensorus service' indicates a retrieval operation with no side effects.
Attacks that exploit this kind of access
Retrieve operational metrics from the Tensorus service. It is categorised as a Read tool in the Tensorus MCP MCP Server, which means it retrieves data without modifying state.
Register the Tensorus MCP server in PolicyLayer and add a rule for management_get_metrics: 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 Tensorus MCP. Nothing to install.
management_get_metrics 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 management_get_metrics 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 management_get_metrics. 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.
management_get_metrics is provided by the Tensorus MCP server (tensorus/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 →