Get the FREE Ultimate OpenClaw Setup Guide →

openops

The batteries-included, No-Code FinOps automation platform, with the AI you trust.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio openops-cloud-openops docker run -i openops/openops:latest \
  --env OPENOPS_API_KEY="your-api-key-here" \
  --env OPENOPS_INSTANCE="default"

How to use

OpenOps is a No-Code FinOps automation platform that helps organizations optimize cloud spend and financial operations. The MCP server provided here is packaged as a Docker image which you can run to access OpenOps automation capabilities in your environment. Once the container is running, you can leverage OpenOps workflows to design, customize, and execute cost-optimization tasks, allocation rules, anomaly detection, and safe de-provisioning—without writing code. The platform also exposes integration points to connect with major cloud providers, analysis tools, and collaboration channels, enabling teams to trigger workflows from familiar channels and dashboards.

To use the MCP server, start by running the Docker image and ensuring the required environment variables are set (for example, API keys or instance identifiers). After startup, you can interact with OpenOps via its web UI or API endpoints (as documented in the OpenOps docs). Use the included No-Code editor to assemble or modify workflows, then test changes in a controlled environment before applying them to production. The platform supports versioning and traceability so you can audit workflow steps and revert to previous configurations if needed.

How to install

Prerequisites:

  • Docker installed on the host (Docker Engine 19.03+)
  • Optional: docker-compose if you prefer compose-based deployment

Step 1: Install Docker

Step 2: Pull and run the OpenOps Docker image

  • Basic run (interactive): docker run -e OPENOPS_API_KEY=your-api-key -e OPENOPS_INSTANCE=default -i openops/openops:latest

Step 3: Verify startup

  • Check logs to ensure the service started correctly: docker ps docker logs <container_id>

Step 4: Access the platform

  • OpenOps will expose its UI/API at the container’s mapped ports. If you’re running locally, navigate to the host URL as documented by the OpenOps deployment guide. Configure your cloud provider connections, create/work with workflows, and tailor them to your FinOps needs.

Step 5: Optional compose-based deployment

  • If you prefer docker-compose, create a docker-compose.yml with the following (adjust image and envs as needed): version: '3.8' services: openops: image: openops/openops:latest environment: - OPENOPS_API_KEY=your-api-key - OPENOPS_INSTANCE=default ports: - "8080:8080" restart: unless-stopped
  • Then run: docker-compose up -d

Additional notes

Tips:

  • Ensure OPENOPS_API_KEY is kept secure and rotated as per your security policy.
  • If you run behind a reverse proxy, configure TLS and proper host headers according to the OpenOps docs.
  • Review workflow versioning and audit logs to track changes and deployments.
  • If you encounter connectivity issues to cloud providers, verify network egress rules and API access permissions in your cloud accounts.
  • Check for updates to the OpenOps Docker image regularly to apply improvements and security patches.

Related MCP Servers

Sponsor this space

Reach thousands of developers