define_custom_metric
AI agents use define_custom_metric to create or update resources in Ai Analyst — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ai Analyst environment.
The name implies creating/writing a new custom metric definition, which is a reversible write operation. Sibling tool 'delete_custom_metric' further supports that custom metrics can be created and deleted, confirming this is a Write action. Confidence is reduced due to the empty description.
From the tool's definition Tool name 'define_custom_metric' suggests creating or defining a new custom metric; description is empty and uninformative.
Attacks that exploit this kind of access
define_custom_metric. It is categorised as a Write tool in the Ai Analyst MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ai Analyst MCP server in PolicyLayer and add a rule for define_custom_metric: 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 Ai Analyst. Nothing to install.
define_custom_metric is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the define_custom_metric 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 define_custom_metric. 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.
define_custom_metric is provided by the Ai Analyst MCP server (sbdk-dev/local-ai-analyst). 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 →