Cloud cost management MCP server for Azure: spending, forecasts, anomalies, budgets, advisor.
Cloud cost management MCP server for Azure: spending, forecasts, anomalies, budgets, advisor. The cloudscope mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.
Ask once: "Give me this month's cost review" — and CloudScope runs the full workflow (spend, deltas, anomalies, idle resources, budgets, forecast) and hands back a decision-ready report, not raw numbers to interpret yourself:
The server ships on npm as cloudscope-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
Everything the assistant can do here goes through one of these:
get_cost_summary — Spending breakdown by service, group, or regionget_cost_by_tag — Costs grouped by a tag/label keycompare_periods — Side-by-side cost comparison of two date rangestop_spending_resources — Most expensive individual resourcesget_cross_subscription_costs — Combined costs across Azure subscriptionsget_cross_project_costs — Combined costs across GCP projectsdetect_anomalies — Find spending spikes vs previous periodcheck_budgets — Budget status, current spend, projected overageget_cost_forecast — Predict spending based on current trendslist_recommendations — Cost optimization suggestions (Azure Advisor / GCP Recommender)find_idle_resources — Provisioned but unused resources with cost estimatesfind_untagged_resources — Resources with no tags/labels (cost attribution gaps)You will need 8 environment variables: AZURE_SUBSCRIPTION_ID, GOOGLE_CLOUD_PROJECT, GCP_BILLING_TABLE, AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET, GCP_PROJECT_ID, GCP_BILLING_ACCOUNT_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Cloudscope's toolset — get_cost_summary, get_cost_by_tag, compare_periods and 11 more — is a fair guide to whether it matches your workflow. It is maintained by alexpota; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Cloudscope's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| get_cost_summary | Spending breakdown by service, group, or region |
| get_cost_by_tag | Costs grouped by a tag/label key |
| compare_periods | Side-by-side cost comparison of two date ranges |
| top_spending_resources | Most expensive individual resources |
| get_cross_subscription_costs | Combined costs across Azure subscriptions |
| get_cross_project_costs | Combined costs across GCP projects |
| detect_anomalies | Find spending spikes vs previous period |
| check_budgets | Budget status, current spend, projected overage |
| get_cost_forecast | Predict spending based on current trends |
| list_recommendations | Cost optimization suggestions (Azure Advisor / GCP Recommender) |
| find_idle_resources | Provisioned but unused resources with cost estimates |
| find_untagged_resources | Resources with no tags/labels (cost attribution gaps) |
| get_current_date | Today's date and current/previous month bounds |
| list_subscriptions | Azure subscriptions with active indicator |
{
"mcpServers": {
"cloudscope": {
"command": "npx",
"args": ["-y", "cloudscope-mcp"]
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| AZURE_SUBSCRIPTION_ID | Configuration value read at startup. | Optional |
| GOOGLE_CLOUD_PROJECT | Configuration value read at startup. | Optional |
| GCP_BILLING_TABLE | Configuration value read at startup. | Optional |
| AZURE_TENANT_ID | Configuration value read at startup. | Optional |
| AZURE_CLIENT_ID | Configuration value read at startup. | Optional |
| AZURE_CLIENT_SECRET | Credential the server authenticates with. | Yes |
| GCP_PROJECT_ID | Configuration value read at startup. | Optional |
| GCP_BILLING_ACCOUNT_ID | Configuration value read at startup. | Optional |
Manage your whole Supabase project in conversation — database, auth, storage, Edge Functions and branches.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
AWS Labs' official server suite — current AWS docs, CDK guidance, cost analysis and service tools.
Cloud browsers for AI agents — automation sessions that run in Browserbase's fleet, not on your machine.
Workers, KV, R2 and D1 by conversation — Cloudflare's official remote servers for building and observability.
Dashboards, Prometheus and Loki queries, incidents and alerts — observability by conversation.