LABSCO SUMMARY

Two rate limits and one pagination cliff to plan around.

The spending estimate is limited to 10 requests per user per minute and 20 per organisation per minute, so it is not something to poll. For large reports, the queued path pages at 30,000 rows against 10,000 for the synchronous one and has no timeout, which is the difference between a report that completes and one that dies halfway. Also worth knowing before you parse anything: responses use the Cloudability v3 envelope, so the fields sit under a result object rather than at the top level.

What it is

A wide client for the Cloudability v3 API, weighted towards container cost allocation — which namespace, workload or team is actually consuming the cluster spend — with budgets, forecasts and general cost reporting alongside.

What you get

containers_report is the centre of it: fairshare and allocated cost by namespace, workload, cluster or label, with filtering and pagination
Container support tools: get_container_resource_usage for daily trends and rightsizing, discover_container_labels for the labels available to group by, get_detailed_cluster_info, list_clusters, provision_kubernetes_cluster and get_cluster_deployment_yaml
Spend projection: get_spending_estimate for the current month with service-level drivers and daily progression, get_spending_forecast for multiple months with configurable history and options to strip credits and one-time charges
Budgets: list_budgets, get_budget, create_new_budget, modify_budget, remove_budget, plus create_budget_alert, list_budget_alerts, modify_budget_alert and remove_budget_alert
Cost reporting: execute_cost_report with up to 15 dimensions, up to 8 metrics, twelve filter operators, multi-column sorting and relative dates; queue_cost_report with check_report_status and get_queued_report_results for large runs
Discovery: get_available_measures and get_filter_operators, plus list_saved_cost_reports
Vendor account listings for AWS, Azure, GCP, IBM Cloud and OCI

Requirements

Python 3.14+ and uv — clone the repository, run uv sync, and launch main.py. CLOUDABILITY_API_URL selects the region among US, EU, APAC and ME. Authentication is one of three: Frontdoor API keys in CLOUDABILITY_KEY_ACCESS and CLOUDABILITY_KEY_SECRET, which lets the server acquire tokens itself; a bearer token passed per call; or legacy basic auth. CLOUDABILITY_ENVIRONMENT_ID comes from your Access Administration environment, and CLOUDABILITY_DEFAULT_VIEW_ID is required for the container and cluster calls.

Setup effort

Build from source — clone the repository, then follow the project's own run instructions

See installation options

USE CASES

01

Finding out which team is spending the cluster budget

Group container costs by a team label rather than by namespace, once you know which labels exist.

discover_container_labelscontainers_report

02

Answering how the month is tracking

Pull the month-to-date estimate with its service-level breakdown and compare against last month's actuals.

get_spending_estimate

03

Setting a budget and being told when it slips

Create the budget with its thresholds, then subscribe to alerts for exceeded and projected breaches.

create_new_budgetcreate_budget_alert

04

Running a report too large to return at once

Queue it, poll the status, and collect the results instead of timing out on a synchronous call.

queue_cost_reportcheck_report_statusget_queued_report_results

30 tools

Listed in project docs. Your client may show a different list.

provision_kubernetes_cluster

get_cluster_deployment_yaml

containers_report

get_container_resource_usage

discover_container_labels

get_detailed_cluster_info

list_clusters

list_budgets

get_budget

list_aws_accounts

list_azure_accounts

list_gcp_accounts

list_ibm_accounts

list_oci_accounts

get_spending_estimate

BEFORE YOU INSTALL

What to know first

Tools you get

30 tools named in the project's documentation.

Requires

Python 3.14+
CLOUDABILITY_KEY_ACCESS in your environment
CLOUDABILITY_KEY_SECRET in your environment
CLOUDABILITY_ENVIRONMENT_ID in your environment

Where it runs

The documented client runs the server on your machine.

INSTALLATION

Connect your client

Server setup

TERMINAL

git clone https://github.com/eelzinaty/cloudability-mcp-server.git

MCP Clients

Any MCP client

ANY MCP CLIENT · JSON

{
  "mcpServers": {
    "cloudability": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "main.py"
      ],
      "cwd": "<YOUR_PATH_TO_CLOUDABILITY_MCP_SERVER>",
      "env": {
        "CLOUDABILITY_API_URL": "https://api.cloudability.com/v3",
        "CLOUDABILITY_ENVIRONMENT_ID": "<YOUR_CLOUDABILITY_ENVIRONMENT_ID>",
        "CLOUDABILITY_DEFAULT_VIEW_ID": "12345",
        "CLOUDABILITY_KEY_ACCESS": "<YOUR_CLOUDABILITY_KEY_ACCESS>",
        "CLOUDABILITY_KEY_SECRET": "<YOUR_CLOUDABILITY_KEY_SECRET>",
        "CLOUDABILITY_FRONTDOOR_URL": "https://frontdoor.apptio.com/service/apikeylogin"
      }
    }
  }
}

Cloudability API