create_indicator
Create an indicator: name the measure, DEFINE it (how it is computed, so two people read the same number), give its unit, its direction (up = higher is better, down = lower is better), whether it is leading (moves before the outcome) or lagging (the outcome itself), its target and the source the ...
This record as markdown: /tools/adrata-adrata-mcp/create-indicator.md
What create_indicator does on Adrata
AI agents use create_indicator to create or update resources in Adrata, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adrata environment.
Why create_indicator is rated Medium
An AI agent can call create_indicator faster than any human can review: one bad instruction and it creates or modifies resources in Adrata by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs create_indicator safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adrata, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For create_indicator, this is the rule to start with:
create_indicator stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Adrata, apply this rule, and every create_indicator call is checked against it from then on.
Questions about create_indicator
Create an indicator: name the measure, DEFINE it (how it is computed, so two people read the same number), give its unit, its direction (up = higher is better, down = lower is better), whether it is leading (moves before the outcome) or lagging (the outcome itself), its target and the source the readings come from. Attach it to a goal or strategy with goalId. counterOfIndicatorId names the indicator this one guards against Goodhart. It is categorised as a Write tool in the Adrata MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Adrata MCP server in PolicyLayer and add a rule for create_indicator: 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 Adrata. Nothing to install.
create_indicator 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 create_indicator 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 create_indicator. 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.
create_indicator is provided by the Adrata MCP server (@adrata/adrata-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adrata, and thousands of servers like it.
This server
Across the catalogue