@clocknext/mcp

The ClockNext MCP server — meter usage, verify signals, and manage usage‑based billing directly from AI coding tools (Claude Code, Cursor, Codex, Antigravity) and any other Model Context Protocol client.

It runs locally over stdio: your AI tool spawns it as a subprocess, and your organisation's cnk_… API key stays in the server's environment — never in the model's context.

Install as a Claude Code plugin (recommended)

In Claude Code:

/plugin marketplace add ClockNext/clocknext-mcp
/plugin install clocknext@clocknext

Claude Code prompts for your ClockNext API key at install (stored securely) and wires the server up automatically — no manual config, no env vars. Run /mcp to confirm the clocknext tools are available.

Related MCP server: 0nMCP

Manual setup (other MCP clients)

You need a ClockNext API key (Settings → API Keys). Then add the server to your tool's MCP config.

Claude Code

claude mcp add clocknext --env CLOCKNEXT_API_KEY=cnk_your_key -- npx -y @clocknext/mcp

Cursor / Windsurf / Antigravity — .cursor/mcp.json (or the tool's MCP JSON):

{
  "mcpServers": {
    "clocknext": {
      "command": "npx",
      "args": ["-y", "@clocknext/mcp"],
      "env": { "CLOCKNEXT_API_KEY": "cnk_your_key" }
    }
  }
}

Codex — ~/.codex/config.toml:

[mcp_servers.clocknext]
command = "npx"
args = ["-y", "@clocknext/mcp"]
env = { CLOCKNEXT_API_KEY = "cnk_your_key" }

Environment

Tools

A typical agent flow: whoami → list_models → verify_signal (confirm the customer/model/plan price correctly) → record_usage.

Development

npm install          # links the local @clocknext/sdk (file:../clocknext-sdk)
npm run build        # tsup → dist/index.js (executable bin)
npm run dev          # run from source via tsx
CLOCKNEXT_API_KEY=cnk_... npm start

Built on the official @modelcontextprotocol/sdk over @clocknext/sdk. stdio today; a hosted Streamable‑HTTP variant is planned. Logs go to stderr (stdout is the protocol channel).