get_gcp_recommendation
Evaluate current GCP commitments, plan and automate purchases, and optimize cloud costs with PerfectScale for Commitments. Returns the recommendation for one product line (gcp_service) and region scope on the GCP billing account, including analysis metrics and time-bucketed eligible spend. Use gr...
This record as markdown: /tools/doit/get-gcp-recommendation.md
What get_gcp_recommendation does on Doit
AI agents call get_gcp_recommendation 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 |
|---|---|---|---|
region | string | — | GCP region scope in the DCI `lower_snake_case` wire form (for example `us_east1`), or the literal `global` for cross-region scopes. This is not the raw provider |
X-Tenant-Id | string | — | |
gcp_service | string | Yes | |
granularity | string | — | |
customerContext | string | — | Scope the request to a specific customer by ID. Required for DoiT employees (whose token isn't tied to a single customer); omit for direct customer users. |
billingAccountId | string | Yes |
Parameters from the server's own tool schema.
Why get_gcp_recommendation is rated Low
Even though get_gcp_recommendation 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_gcp_recommendation 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_gcp_recommendation, this is the rule to start with:
get_gcp_recommendation 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_gcp_recommendation call is checked against it from then on.
Questions about get_gcp_recommendation
Evaluate current GCP commitments, plan and automate purchases, and optimize cloud costs with PerfectScale for Commitments. Returns the recommendation for one product line (gcp_service) and region scope on the GCP billing account, including analysis metrics and time-bucketed eligible spend. Use granularity to choose the eligible-spend bucket size (defaults to day). region: optional for compute, defaulting to global (its only scope). Required for cloud_sql — omitting it returns 400 with code validation_failed, as does a malformed region or one incompatible with gcp_service (cloud_sql never uses global). A well-formed region the billing account has never had eligible spend in returns 404 with code not_found — the scope does not exist, same as an unknown billing account. When the scope exists but no stored recommendation matches, the response is 200 with recommendation omitted and estimatedEquivalentRecommendedCommitment of 0. It is categorised as a Read tool in the Doit MCP Server, which means it retrieves data without modifying state.
get_gcp_recommendation accepts 6 parameters: region, X-Tenant-Id, gcp_service, granularity, customerContext, billingAccountId. Required: gcp_service, billingAccountId. 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_gcp_recommendation: 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_gcp_recommendation 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_gcp_recommendation 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_gcp_recommendation. 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_gcp_recommendation 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