mcpField
O
OPS

OPS

Local
github.com/nanovmsCloud & Infra4Updated 73w ago
Repository

About OPS

OPS is an MCP server for building, deploying, and orchestrating unikernels across cloud providers. It lets MCP clients list images and instances and create instances.

Key features

  1. 01Build and deploy unikernels
  2. 02Orchestrate cloud instances
  3. 03List instances
  4. 04List images
  5. 05Create instances

Use cases

  1. 01Inspect available images and instances
  2. 02Create a unikernel instance
  3. 03Manage unikernel deployments across clouds

MCP support

OPS exposes tools to MCP clients for listing instances and images, and creating instances.

#devops#unikernels#cloud

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ops-mcp

mcp server for ops

Build like normally.

Put this in your Claud config:

~/Library/Application Support/Claude/claude_desktop_config.json

Ensure your command is in the right path and more importantly the PATH env is set to run.

{
"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"
        }
    }
  }
}

Available tools:

List instances

List images

Instance create <image_name>

Instance create redis-server

Note: Very open to suggestions on how this all should work as this initial cut was done not having ever used Claude or MCP.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.