MCP.Market

Clocknext MCP server

by Clocknext·io.github.Clocknext/mcp·v0.13.0
No reviews yet

Meter usage and manage usage-based billing from AI tools via the ClockNext API.

B72/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B72/100

full report

Adoption
Growing

0 stars550 downloads/wk

Reviews

Write one

Nobody has reviewed Clocknext yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Clocknext tools (20, 5 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • clocknext_add_model
  • clocknext_archive_composite
  • clocknext_bulk_import_customers
  • clocknext_create_compositewrite action
  • clocknext_create_customerwrite action
  • clocknext_create_purchasewrite action
  • clocknext_get_composite

    Get one composite in full by id \u2014 name, refId, price, description, active state, and the credits / outcomes / units it wraps (with their agentKeys).

  • clocknext_get_customer

    Fetch one customer by ClockNext id.

  • clocknext_get_customer_balances

    Fetch a customer's current wallet / credit / outcome / unit balances. Use it to confirm a purchase granted the expected entitlements, or that a test signal drew the balance down as expected.

  • clocknext_get_customer_plan

    Fetch a customer's current active plan (from their purchase). Use it to confirm a customer is subscribed to the plan you expect before firing a test signal.

  • clocknext_get_customer_usage

    Read back a customer's recent usage logs (most recent first). Use it to CONFIRM a signal landed \u2014 after running the product's code so it fires a real signal, check the event shows up with the expected model, tokens, and cost. This is the ONLY proof a real signal landed: the MCP cannot record usage, and ingest is asynchronous, so a signal your code 'sent' is not billed until it appears here.

  • clocknext_get_doc
  • clocknext_list_composites
  • clocknext_list_customers

    List / search the org's customers, most-recent first (cursor-paginated). Use it to find a customer id or check whether one already exists before creating.

  • clocknext_list_models

    List the models the organisation has enabled, with their USD prices per 1,000,000 tokens. Use a returned `modelId` as the `model` when verifying or recording usage. Pass active=true to see only models that can be metered right now.

  • clocknext_search_docs
  • clocknext_unarchive_composite

    Reactivate an archived composite (sets isActive\u2192true) \u2014 the reverse of clocknext_archive_composite. Same refId, same wrapped items; its tag resolves again for new signals. Prefer this over creating a replacement.

  • clocknext_update_compositewrite action
  • clocknext_whoami
  • clocknext_write_envwrite action

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

1 medium
  • Code scan2 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/index.js: …ode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…
Overall 72/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Clocknext compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
72/100
higher than 37% of 48,243 servers
Tools
20
the typical server has 7
Tools that change things
25%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
550
more than 89% of 12,306 servers with a package

What its tools let an agent do: 15 read · 5 change

Release history: 3 versions in the registry since 2026-09-12, latest 2026-10-01, typically one every 17 days.

Install Clocknext in Claude Code, Cursor or VS Code

Runs npx -y @clocknext/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @clocknext/mcp
Add to Cursor

What the publisher says

From the Clocknext repository's README, as published. We do not edit it. Read it on GitHub

@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.

This repo ships two things:

full setup using those tools (human‑in‑the‑loop, sandbox‑first).

  • the MCP server (@clocknext/mcp) — the tools an agent calls.
  • the clocknext-onboarding skill — the step‑by‑step playbook that drives a

Install them together (the Claude Code plugin) or separately. Pick by what you want and which agent you're on:

The skill and the MCP server work together — the skill drives the tools — so for the full guided experience install both (or just use the plugin, which bundles them). The plugin is the one‑command option, but Claude Code only.

A ClockNext API key is required for the tools: Settings → API Keys →

cnk_…. It is a server‑side secret — keep it in env/secret config, never in

client code or a repo.

1 — The skill (every AI coding agent)

The clocknext-onboarding skill is the guided playbook (detect models → entitlements → plan → meter the codebase → test with a dummy customer). It drives the MCP tools, so install the MCP server too (§2 below) — the skill on its own has nothing to call.

Install it with npx skills — one command, works across Claude Code, Cursor, Codex, Windsurf, Gemini, Antigravity, VS Code, and ~20 other agents. Target your agent with --agent so it lands where that agent actually looks:

# user-wide (all projects), for a specific agent:
npx skills add ClockNext/clocknext-mcp --global --agent claude-code
# …or this project only:
npx skills add ClockNext/clocknext-mcp --agent claude-code

Swap claude-code for cursor, codex, windsurf, … (or for every detected agent). npx skills list shows what's installed; npx skills remove clocknext-onboarding removes it. After installing, restart the agent** — most load skills at startup.

Claude Code, read this. Claude Code only loads skills from

~/.claude/skills/, .claude/skills/, or a plugin — not the CLI's default

universal .agents/skills/ folder. So you must pass --agent claude-code

(as above), which installs to ~/.claude/skills/ (with --global) or

.claude/skills/. A bare npx skills add … puts it in .agents/skills/, where

Claude Code will never see it. Simplest of all for Claude Code: use the

plugin — it registers the skill

natively and wires the MCP in one step.

Manual install (no CLI)

Copy the folder from the repo into your agent's skills directory:

git clone https://github.com/ClockNext/clocknext-mcp
# Claude Code — all projects:
mkdir -p ~/.claude/skills && cp -r clocknext-mcp/skills/clocknext-onboarding ~/.claude/skills/
# …or this project only: .claude/skills/

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Clocknext: common questions

Is Clocknext MCP server safe?
Mostly: it is graded B (72/100). Read the Clocknext safety report
How do I install Clocknext?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Clocknext need an API key?
Yes. The registry entry asks for CLOCKNEXT_API_KEY.
Is Clocknext maintained?
The last commit was 35 days ago (2026-10-01). The latest release is v0.13.0.
How does Clocknext compare with other MCP servers?
safety score 72/100 (higher than 37% of 48,243 servers); tools 20 (the typical server has 7); tools that change things 25% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.