mcpField
C
Clara by nOps

Clara by nOps

Remote
nops.ioOther2Updated 1d ago

About Clara by nOps

Clara by nOps is a FinOps assistant for querying cloud costs, commitments, budgets, and reports across AWS, GCP, and Azure. Its MCP plugins and standalone setup instructions support connection from multiple AI clients.

Key features

  1. 01Query cloud cost data
  2. 02Review commitments and budgets
  3. 03Retrieve cost reports
  4. 04Use plugins for Claude and Cursor
  5. 05Authenticate through OAuth

Use cases

  1. 01Query spending across AWS, GCP, or Azure
  2. 02Review cloud budgets and commitments
  3. 03Retrieve cloud cost reports from an AI client

MCP support

Clara is a remote MCP server accessed over HTTP by compatible clients; its Claude and Cursor plugins configure the server automatically, while other clients can use manual configuration. Authentication uses OAuth on first use.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.nops.io
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Clara MCP Plugins

Install packages and setup guides for connecting Clara to Claude, Cursor, and other AI clients.

Supported clients

ClientInstall guide
Claudedocs/install-claude.md
Cursordocs/install-cursor.md

Standalone MCP setup

The Claude and Cursor plugins above include the MCP server config and register it automatically. If you're using a different MCP-compatible client, add the following manually:

{
  "mcpServers": {
    "clara": {
      "type": "http",
      "url": "https://mcp.nops.io"
    }
  }
}

Claude Code — add to .mcp.json in your project root, or to ~/.claude/mcp.json for global access.

Cursor — add to .cursor/mcp.json in your project root, or to ~/.cursor/mcp.json for global access.

Gemini CLI — gemini extensions install https://github.com/nops-io/clara-mcp

Other clients — consult your client's MCP documentation for where to place server configuration.

Clara is also published to the official MCP Registry as io.github.nops-io/clara (see server.json).

Clara authenticates via OAuth on first use. See docs/auth.md for details.

Authentication

Clara authenticates via OAuth on first use. See docs/auth.md.

Troubleshooting

See docs/troubleshooting.md.

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.