get_insight
Use this when the user wants the details and aggregate summary (savings, risk counts, status, description) of a single optimization insight identified by its source and key. Returns the insight metadata only — it does NOT include the individual affected resources (use get_insight_resources for th...
This record as markdown: /tools/doit/get-insight.md
What get_insight does on Doit
AI agents call get_insight to retrieve information from Doit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
key | string | Yes | The key of the insight (e.g. 'delete-ebs-volumes'). Use the 'key' field from list_optimization_recommendations. |
source | string | Yes | The source of the insight (e.g. 'aws-cost-optimization-hub', 'aws-trusted-advisor'). Use the 'source' field from list_optimization_recommendations. |
Parameters from the server's own tool schema.
Why get_insight is rated Low
Even though get_insight only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs get_insight safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Doit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_insight, this is the rule to start with:
get_insight is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Doit, apply this rule, and every get_insight call is checked against it from then on.
Questions about get_insight
Use this when the user wants the details and aggregate summary (savings, risk counts, status, description) of a single optimization insight identified by its source and key. Returns the insight metadata only — it does NOT include the individual affected resources (use get_insight_resources for those) and is not for listing all insights (use list_optimization_recommendations). It is categorised as a Read tool in the Doit MCP Server, which means it retrieves data without modifying state.
get_insight accepts 2 parameters: key, source. Required: key, source. The full parameter table on this page comes from the server's own tool schema.
Register the Doit MCP server in PolicyLayer and add a rule for get_insight: 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 Doit. Nothing to install.
get_insight 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 get_insight 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 get_insight. 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.
get_insight is provided by the Doit MCP server (@doitintl/doit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Doit, and thousands of servers like it.
This server
Across the catalogue