nable (finops-mcp)
nable (finops-mcp) is a local-first FinOps MCP server that connects to AWS, Azure, GCP, Kubernetes, and 15+ SaaS providers (Datadog, Snowflake, OpenAI, etc.) to manage and optimize cloud costs directly inside AI editors like Claude and Cursor. Credentials are stored in the OS keychain and data stays local—no backend servers.
Here's what you can do:
Cost Visibility & Reporting
Summarize costs broken down by service, account, region, provider, or team (tag attribution)
Compare spend across cloud and SaaS providers; view daily/monthly trends and top cost drivers
Get a grand total combining cloud infrastructure + SaaS spend
Export reports as HTML or CSV; generate visual dashboards
Anomaly Detection & Alerts
Detect cost spikes/drops using z-score, CUSUM drift, and seasonal normalization
Set custom alert policies (thresholds, muting, glob patterns); acknowledge expected anomalies
Send on-demand or scheduled cost digests to Slack/Teams/email
Cost Optimization & Waste Detection
AWS: EC2/RDS/ECS Fargate rightsizing, idle resource detection (NAT Gateways, EBS, load balancers, Elastic IPs), CloudWatch log retention, S3 multipart cleanup, ECR image cleanup, public IPv4 audit, network/data transfer analysis, deep waste audit
Azure: VM rightsizing, Azure Advisor recommendations, reservation utilization, cost forecasts
GCP: Unattached disks, idle IPs, old snapshots, idle VMs
List and optionally clean up idle resources (with dry-run safety gate)
Kubernetes Cost Management
Break down costs by namespace, workload, label, or Helm release
Detect wasted spend, score cluster efficiency, estimate cost impact of a
helm diffbefore applyingCompare multiple clusters; label-based chargeback
Commitment & Rate Analysis
Analyze Reserved Instance and Savings Plan coverage, utilization, and waste
Savings Plan showback by team/tag; detect EDP discounts and private pricing
Budget Management
Create/update/delete budgets scoped to total, provider, team, or service
Check budget status; sync budgets from a YAML file for version-controlled limits
Savings Tracking & Recommendations
Track recommendations through their lifecycle (open → acted on → verified → dismissed)
View a savings ledger; measure recommendation accuracy over time with adaptive learning
Ticketing & Workflow Automation
Create tickets in Jira, Linear, or GitHub Issues for anomalies, rightsizing, K8s waste, or scorecard gaps
Efficiency Scorecard
Compute a 0–100 FinOps score across 5 dimensions: compute, waste, commitment, tag hygiene, and anomaly response
Compare team-level scorecards side by side
AWS Organizations & CUR/Athena (Team Plan)
Org-wide cost rollup with per-account and OU breakdowns
Per-resource costs, RI waste detail, and tag breakdowns from CUR via Athena
Infrastructure & Configuration
Manage multiple profiles for multi-account/multi-client setups
Check connector health, list configured accounts, run tag attribution, take cost snapshots on demand
Send onboarding/welcome emails; configure Slack and Teams notifications
Retrieves billing data from Cloudflare's Billing API for cost analysis.
Fetches real-time cost data from Datadog's Usage Metering API, enabling analysis of Datadog spend.
Retrieves GitHub Actions usage and Copilot seat costs for cost management.
Automates creation of Jira tickets for cost optimization recommendations, such as EC2 waste.
Retrieves MongoDB Atlas invoice data for cost monitoring.
Fetches data ingest volumes and user counts from New Relic for cost analysis.
Publishes cost analysis findings and reports to Notion for team collaboration.
Retrieves PagerDuty seat count for cost tracking.
Sends anomaly alerts and cost reports via Slack for real-time notifications.
Retrieves Snowflake usage costs from ACCOUNT_USAGE.METERING_HISTORY.
Fetches Twilio usage records for cost analysis.
Retrieves Vercel invoice data for cost management.
nable
See where your cloud and AI bills go, and spend less. Runs in your terminal or inside Claude, Cursor, and VS Code.
You do not need to be a cloud-cost expert. nable does three things:
Shows what you spend across AWS, Azure, GCP, Kubernetes, and 15+ AI and SaaS providers, in one place.
Finds what you are wasting (idle servers, oversized databases, forgotten storage) and puts a dollar figure on each one.
Fixes it, with your approval, by opening a pull request, then checks your next bill to prove the saving was real.
Built for the engineer who owns the bill, not a dedicated FinOps team. Everything runs on your machine, read-only, and your billing data never leaves it.
Try it
uvx nable scannable scan · profile prod
account 3521… · this account only
scanning 17 regions …
us-east-1 ......... 3 findings
eu-west-1 ......... 1 finding
────────────────────────────────────────────
$2,140/mo recoverable
$1,200/mo 3 idle NAT gateways, us-east-1
$610/mo 14 unattached EBS volumes (2.1 TB), us-east-1
$330/mo idle RDS instance (db.r5.xlarge, <2% CPU), eu-west-1
run `nable scan --spend` for the spend breakdown (uses Cost Explorer, ~$0.02)Reads only free cloud APIs, so scanning never adds to your bill. uvx nable scan --demo runs on sample data with no account at all. Add --json for CI, or --spend for a deeper breakdown.

Related MCP server: cloudscope-mcp
Use it in your editor
uvx nable runs as a local MCP server inside Claude, Cursor, and VS Code, on your existing Claude or Cursor membership, no API key and no per-token cost. Then ask:
"Why did our AWS bill jump last month?"
"How much are we spending on OpenAI and Anthropic?"
"Which instances should we downsize?"
"Open a Jira ticket for any waste over $200/mo"
Setup
Requires Python 3.11+. Need uv? curl -LsSf https://astral.sh/uv/install.sh | sh (or brew install uv).
uvx nableThe setup wizard finds AWS or GCP credentials already on your machine (an SSO login, a CLI profile, or default credentials), connects the one you pick, and configures your editor. Usually you never type a key.
Cursor one-click: Add nable to Cursor
Free forever for the local tool. A hosted version for teams (dashboards without a terminal, SSO, scheduled reports, always-on agents) is at getnable.com/pricing.
If finops setup doesn't auto-configure, run:
finops setup claudeOr add manually to claude_desktop_config.json:
With uvx (recommended):
{
"mcpServers": {
"nable": { "command": "uvx", "args": ["--python", "3.12", "finops-mcp"] }
}
}With absolute path:
{
"mcpServers": {
"nable": { "command": "/usr/local/bin/finops-mcp" }
}
}Use the path from which finops-mcp.
Config file locations:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
Why uvx? Claude Desktop is a GUI app and doesn't inherit your shell's PATH. uvx runs finops-mcp in its own isolated environment. It's the most reliable option on corporate machines with managed Python installs.
nable is not just tools your agent reads from. It is a pre-action gate your agent calls before it makes a cost-affecting change: it prices the change, checks it against your budget, and offers a cheaper path. It never applies anything itself. Propose-only, your agent proposes and a human approves.
Add one line to your agent's system prompt (Claude Code, Cursor, or any MCP client):
Before you apply any infrastructure change (a terraform apply, a helm upgrade, creating or resizing a resource) or start an expensive job, first call
check_action_policywith the action and the change (a terraform plan, a helm diff, or amonthly_delta_usd). Relay the verdict, the dollar impact, and the cheaper path when one is offered. Never apply ablockor anescalateaction; surface it to the human. nable is advisory and propose-only.
The gate returns allow / warn / block / escalate against your policy, the
monthly and annual dollar impact, and a spot alternative when the change is compute.
One-way doors (delete, terminate, buy a commitment) and over-budget changes always
escalate to a human.
And a budget for the agent itself. Run nable ai-budget once, it asks whether
you are on a flat plan or a metered API and what you pay, then remembers. On a flat
plan it tracks how much subsidized compute you pull for your fixed fee and warns
before you run low; on metered it gates on a dollar spend cap. check_ai_budget does
the same for the agent mid-task. It reads your Claude Code usage locally, nothing
uploaded. Add to your system prompt:
Before starting a large task, call
check_ai_budget. If it returnswarnorover, tell me where I stand before continuing.
It reports your real usage and burn rate against your budget, not a fabricated percentage of a plan's hidden rate limit.
Provider | What it pulls |
AWS | Cost Explorer (free tier) · CUR via S3 (Pro: line-item granularity, savings plans, reservations) |
Azure | Cost Management API · Advisor cost recs · VM rightsizing (Azure Monitor) · native budgets · forecast |
GCP | Cloud Billing API + BigQuery export |
Datadog | Usage Metering API v2: real dollar amounts |
Snowflake | ACCOUNT_USAGE.METERING_HISTORY |
Langfuse | Daily metrics API: model cost, token usage, trace volume |
MongoDB Atlas | Invoice API |
Twilio | Usage Records API |
Cloudflare | Billing API |
Vercel | Invoice API (Enterprise) |
New Relic | Data ingest + user counts |
Stripe | Fees and billing activity |
Databricks | DBU usage and SQL warehouse spend |
OpenAI | API usage and token spend by model |
Anthropic | Claude API usage and token spend |
Azure roles. The Azure tools span three RBAC roles, granted to the service principal on each subscription (run finops doctor to check):
# repeat per subscription
az role assignment create --assignee <client-id> --role 'Cost Management Reader' --scope /subscriptions/<sub-id>
az role assignment create --assignee <client-id> --role Reader --scope /subscriptions/<sub-id>
az role assignment create --assignee <client-id> --role 'Monitoring Reader' --scope /subscriptions/<sub-id>Is nable free? Yes. The terminal scan, every cost query, anomaly detection, all waste and rightsizing findings, and every connector are free forever. The agent team, ticket auto-creation, scheduled digests, and commitment recommendations are Pro.
Does my billing data leave my machine? No. nable is local-first and read-only by default. It reads your cost data on your machine and never uploads it, and you can confirm the no-egress behavior in the source.
What clouds and providers does it support? AWS, Azure, GCP, and Vertex; Kubernetes (Kubecost, OpenCost); AI and LLM providers (OpenAI, Anthropic, Bedrock, OpenRouter, LiteLLM, Modal, Together, Replicate, Cohere, Mistral, Langfuse); data platforms (Databricks, Snowflake, MongoDB); and SaaS (Datadog, New Relic, Cloudflare, Twilio, Vercel, Stripe).
How is it different from AWS Cost Explorer? Cost Explorer is AWS-only and console-bound. nable is cross-cloud, runs in your terminal and in Claude/Cursor, covers AI and GPU spend no cloud console shows, and proposes fixes as pull requests. nable scan also makes zero paid API calls by default.
Is there an open-source alternative to Vantage or CloudHealth? nable is an open-source (Apache-2.0), local-first alternative for cost queries, waste detection, rightsizing, and AI/GPU cost, running on your machine instead of a hosted SaaS.
finops-doctor # checks credentials, DB, network, audit log
finops setup claude # re-run editor configuration onlySymptom | Fix |
Tools don't appear in Claude | Switch to uvx config or use absolute path |
| Re-install with |
AWS returns no data | Run |
| Your Python is older than 3.11. Install on 3.11+ ( |
| uv tried to compile on Python 3.10. Use 3.11+: |
Corporate SSL errors |
|
Works at home, not at work | Use |
License
Apache-2.0 in full. The hosted enterprise layer (web dashboard, SSO, control plane) lives in a separate private repo. Full tool list in CAPABILITIES.md.
getnable.com · Docs · Privacy · Security
mcp-name: io.github.getnable/finops-mcp
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server for unified cost tracking and analysis across AWS, OpenAI, and Anthropic. It enables users to query expenditures, compare costs across providers, and analyze usage trends through natural language.Last updated10MIT
- AlicenseAqualityCmaintenanceCloud cost management MCP server for Azure. Ask your AI about your cloud bill.Last updated15681MIT
- Alicense-qualityCmaintenanceEnables natural language analysis of AWS costs, automated FinOps waste audits, and budget monitoring across multiple profiles and regions while keeping credentials secure locally.Last updated181MIT
- Alicense-qualityDmaintenanceAnalyzes Azure cloud costs, audits for waste, and provides budget insights via natural language through a secure local MCP server.Last updated2MIT
Related MCP Connectors
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Agent Cost Allocator MCP — multi-tenant LLM cost attribution for chargeback billing. Companion to
User-owned memory for AI agents, Copilot, Claude, IDEs, CLIs, and chat apps over remote MCP.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/getnable/finopsmcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server