Skip to main content

Ask Claude about your cloud costs. AWS, Azure, GCP, Datadog, Snowflake, and 13 more connectors.

Project description

nable: Cloud Cost Intelligence for Claude

Ask Claude about your cloud costs in plain English.

nable is an MCP server that connects Claude Desktop, Cursor, Windsurf, and any MCP-compatible AI client to your real billing data across AWS, Azure, GCP, and 10+ SaaS tools.

"What drove our AWS costs up 40% this month?"
"Which team is spending the most on Datadog?"
"Show me rightsizing opportunities for EC2."
"Create a Jira ticket for any anomalies over $500."

No dashboards. No SQL. Just ask.


Quick start

Option A — uvx (recommended, works everywhere including corporate machines):

pip install uv          # or: brew install uv
uvx finops-mcp setup    # installs in isolated venv, no PATH issues

Option B — pip:

pip install finops-mcp
finops setup            # connects your providers and auto-configures Claude Desktop

finops setup detects Claude Desktop and writes claude_desktop_config.json automatically. It picks uvx if available, otherwise uses the absolute binary path. Restart Claude Desktop and ask: "What are my AWS costs this month?"

14-day free trial, all features unlocked. No credit card required.


Manual Claude Desktop config

If finops setup doesn't auto-configure, run:

finops setup claude

Or add manually to claude_desktop_config.json:

With uvx (recommended):

{
  "mcpServers": {
    "finops": { "command": "uvx", "args": ["finops-mcp"] }
  }
}

With absolute path:

{
  "mcpServers": {
    "finops": { "command": "/usr/local/bin/finops-mcp" }
  }
}

Use the path from which finops-mcp.

Config file locations:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

Why uvx? Claude Desktop is a GUI app and doesn't inherit your shell's PATH. uvx sidesteps this by running finops-mcp in its own isolated environment. It's the most reliable option on corporate machines with managed Python installs.


Troubleshooting

finops-doctor          # checks credentials, DB, network, audit log
finops setup claude    # re-run Claude Desktop configuration only
Symptom Fix
Tools don't appear in Claude Switch to uvx config or use absolute path
command not found: finops-mcp Re-install with pip install finops-mcp or use uvx
Python 3.8/3.9 errors nable requires Python 3.10+: python3.10 -m pip install finops-mcp
Corporate SSL errors pip install --trusted-host pypi.org --trusted-host files.pythonhosted.org finops-mcp
Permission denied Install to user: pip install --user finops-mcp or use uvx
Works at home, not at work Use uvx — corporate IT often strips custom PATH entries

Connectors

Provider What it pulls
AWS Cost Explorer: real spend, savings plans, reservations
Azure Cost Management API
GCP Cloud Billing API + BigQuery export
Datadog Usage Metering API v2: real dollar amounts
Snowflake ACCOUNT_USAGE.METERING_HISTORY
Stripe Balance Transactions API
MongoDB Atlas Invoice API
Twilio Usage Records API
Cloudflare Billing API
GitHub Actions minutes + Copilot seats
Vercel Invoice API (Enterprise)
PagerDuty Seat count
New Relic Data ingest + user counts

What nable actually does

nable is not just a connector that pipes billing data into Claude. It runs active analysis on your infrastructure and surfaces findings as tools Claude can reason about and act on.

AWS deep audit goes well beyond Cost Explorer. It pulls CloudWatch metrics for every running resource and flags waste that never shows up on your bill until it's too late: gp2 volumes that should be gp3 (20% cheaper, same performance), unattached EBS volumes, idle NAT Gateways costing $32/mo in base charges, RDS backup retention set way too high, CloudWatch Log Groups with no retention policy growing forever, and Lambda functions allocated 2x the memory they actually use. Think of it as Compute Optimizer plus the layer underneath it.

Anomaly detection uses z-score, CUSUM drift, and day-of-week seasonal normalization. When something spikes, it drills into Cost Explorer by tag and tells you which team, environment, or service drove it.

Rightsizing combines AWS Compute Optimizer with nable's own CloudWatch analysis. It gives you specific recommended instance types with estimated savings, not just a list of underutilized resources.

Commitment analysis (Team plan) models Savings Plans and Reserved Instance coverage against your actual usage. It shows your current effective discount rate, coverage gaps, and what you would save by purchasing additional commitments.


Team plan features

  • Anomaly alerts via Slack or Teams
  • Cost attribution by team, service, or tag
  • Auto-ticketing: creates Jira, Linear, or GitHub issues for anomalies and waste findings
  • Scheduled email reports
  • Commitment purchase recommendations with ROI projections
  • Org-wide multi-account cost rollup
  • Invoice email parsing via IMAP for vendors without APIs

$39.99/mo, 14-day free trial. Subscribe at nable.sh.


Security

Credentials are encrypted with Fernet and stored in your OS keyring (macOS Keychain, Windows Credential Manager, or libsecret on Linux). They never leave your machine. nable never writes to your AWS account unless you explicitly enable cleanup mode.

Run finops setup aws --iam-template to generate a least-privilege IAM policy with exactly the permissions nable needs.


Docs

Full setup guide: nable.sh/docs

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

finops_mcp-0.7.5.tar.gz (428.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

finops_mcp-0.7.5-py3-none-any.whl (307.9 kB view details)

Uploaded Python 3

File details

Details for the file finops_mcp-0.7.5.tar.gz.

File metadata

  • Download URL: finops_mcp-0.7.5.tar.gz
  • Upload date:
  • Size: 428.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.5 cpython/3.10.5 HTTPX/0.28.1

File hashes

Hashes for finops_mcp-0.7.5.tar.gz
Algorithm Hash digest
SHA256 563dca5f35829e5e45e26141c7c127ec814d71dff7bea35f3a3b5393752effe8
MD5 4a2053e43f52fbd3815da3f7d5e6a3cb
BLAKE2b-256 eea2e6bd018ec894c1e46a1bb368870e434671ad0e09720994d5cfc9667698b1

See more details on using hashes here.

File details

Details for the file finops_mcp-0.7.5-py3-none-any.whl.

File metadata

  • Download URL: finops_mcp-0.7.5-py3-none-any.whl
  • Upload date:
  • Size: 307.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Hatch/1.16.5 cpython/3.10.5 HTTPX/0.28.1

File hashes

Hashes for finops_mcp-0.7.5-py3-none-any.whl
Algorithm Hash digest
SHA256 62e6d485eec822dd93cb2e301647059ba19e6ae3a0ebee5201acdfa693779c01
MD5 ee28f275a343ef131974820b5b23c5ba
BLAKE2b-256 6fc4daa939fe7dc8a49a23033fcb4c38d29907b1bb92b8e9d76b54757ee59bda

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page