ops-mcp MCP Server

What does “ops-mcp” MCP Server do?

The ops-mcp MCP Server is designed to interface with the unikernel ecosystem using the nanos/ops toolchain. It acts as a bridge between AI assistants and the powerful features of the OPS platform, allowing AI-driven workflows to interact with and manage unikernel instances and images. By exposing operations such as listing available unikernel images, managing running instances, and creating new unikernel deployments, ops-mcp enables developers and AI clients to automate cloud-native infrastructure tasks efficiently. This server is particularly useful for tasks involving infrastructure automation, cloud deployments, and the management of lightweight, secure unikernels, streamlining the development and operational workflow for teams leveraging nanos/ops.

List of Prompts

No prompt templates are mentioned in the available documentation or repository files.

List of Resources

No explicit resources are documented in the repository or README.

List of Tools

• List instances
  Lists all running or available unikernel instances managed by the OPS toolchain.
• List images
  Retrieves a list of available unikernel images that can be deployed or managed.
• Instance create <image_name>
  Creates a new unikernel instance from a specified image.
• Instance create redis-server
  Specifically creates a new instance running the Redis server unikernel image.

Use Cases of this MCP Server

• Unikernel Instance Management
  Developers can list and monitor all active unikernel instances, streamlining cloud-native infrastructure management.
• Automated Unikernel Deployment
  Enables rapid creation and deployment of unikernel instances from available images, supporting continuous integration and delivery pipelines.
• Image Discovery and Auditing
  Lists all available unikernel images, helping teams audit, select, and manage their deployment artifacts.
• Specialized Service Instantiation
  Allows for quick deployment of pre-configured services (e.g., Redis) as unikernels, minimizing manual setup and maximizing security.
• AI-Driven Infrastructure Automation
  AI agents can use exposed tools to automate infrastructure tasks, reducing manual intervention and operational errors.

How to set it up

Windsurf

No setup instructions for Windsurf are available in the documentation or repository.

Claude

1. Build the ops-mcp server as you would a standard Go application.
2. Locate your Claude configuration file, typically at ~/Library/Application Support/Claude/claude_desktop_config.json.
3. Edit the mcpServers section to include ops-mcp:

   {
     "mcpServers": {
       "ops-mcp": {
         "command": "/Users/eyberg/go/src/github.com/nanovms/ops-mcp/ops-mcp",
         "args": [],
         "env": {
           "HOME":"/Users/eyberg",
           "LOGNAME":"eyberg",
           "PATH":"/bin:/Users/eyberg/.ops/bin",
           "SHELL":"/bin/zsh",
           "USER":"eyberg"
         }
       }
     }
   }
   

4. Save the configuration and ensure that the PATH environment variable includes the directory with the ops-mcp binary.
5. Restart Claude and verify the MCP server is accessible.

Securing API Keys:
You may specify sensitive environment variables in the env section of the configuration.
Example:

"env": {
  "API_KEY": "${YOUR_OPS_API_KEY}"
}

Cursor

No setup instructions for Cursor are available in the documentation or repository.

Cline

No setup instructions for Cline are available in the documentation or repository.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "ops-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “ops-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

ops-mcp provides basic but useful functionality for managing unikernel workloads via MCP, exposing several core tools. However, it lacks documentation on prompt templates and resources, and only includes detailed setup for Claude. The project would benefit from more thorough documentation and wider integration support.

MCP Score

MCP Table Score: 4/10
Reason: While ops-mcp is functional and open source with a basic toolset, it lacks documentation and support for advanced MCP features like prompts, resources, roots, and sampling, limiting its utility for broader AI-driven automation workflows.