MCP.Market

ClockNext MCP server

by ClockNext·io.github.ClockNext/mcp·v0.6.0
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 stars69 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 (15, 2 write)

write = sends, deletes, buys or posts

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

  • clocknext_add_model

    Enable a model for the organisation so usage can be metered against it \u2014 afterwards its `modelId` is valid in clocknext_record_usage / clocknext_verify_signal and appears in clocknext_list_models. Only models in ClockNext's pricing catalog can be added, AUTOPRICED: give the `provider` and `model` (its catalog id) and ClockNext copies that model's input/output/cache prices from the catalog \u2

  • clocknext_bulk_import_customers

    Bulk-create ClockNext customers in ONE request \u2014 for backfilling an existing user base. Pass an array of customers (each needs name + email; up to 200 per call). The whole batch goes to the server in a single call and comes back with a PER-ROW result \u2014 created id, or an error \u2014 so one duplicate/bad row never aborts the batch. Match results back to your users by email. Runs against a

  • clocknext_create_customerwrite action

    Create a ClockNext customer \u2014 the entity you bill (maps to one of your end-users / tenants / organisations). `name` and `email` are required; everything else is optional profile. Returns the customer with its ClockNext `id`, which you pass as `customerId` when subscribing to a plan (clocknext_create_purchase) and when recording usage (clocknext_record_usage).

  • clocknext_create_purchasewrite action

    Subscribe a customer to a plan (a 'purchase') \u2014 this is what activates the plan for that customer. A usage signal only prices if the customer has an active plan whose components match the meter (credit / outcome / unit), so do this after clocknext_create_customer + clocknext_create_plan. Used to wire up a dummy customer before firing test signals.

  • 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 e.g. after running the product's code so it fires a real signal, check the event shows up here with the expected model, tokens, and cost. For a signal you fire directly, clocknext_record_usage already returns the priced log inline, so this is mainly for signals sent by the running codebase.

  • clocknext_get_doc
  • 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_record_usage

    Record ONE real usage signal \u2014 it is metered and billed. Prices the tokens against the model and the customer's plan and returns the resulting usage log. Pass an idempotencyKey to make retries safe (a repeat with the same key returns the original result instead of double-recording). For a no-op preflight, use clocknext_verify_signal instead.

  • clocknext_search_docs
  • clocknext_verify_signal

    Validate and PRICE a usage signal WITHOUT recording it \u2014 a dry run. Returns the projected usage log (cost, credits drawn, applied rules) so you can confirm the customer, model, and plan are wired up correctly before sending real traffic. Records nothing and never bills.

  • clocknext_whoami

    Identify the ClockNext organisation behind the configured API key, and \u2014 crucially \u2014 whether it is a 'sandbox' (a disposable staging twin) or the 'live' organisation. Call this FIRST to confirm you are pointed at the intended workspace before recording any real usage.

Public scan report

scanner v0.1.9 · 2026-09-24 · 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 12 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 38% of 48,255 servers
Tools
15
the typical server has 7
Tools that change things
13%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
69
more than 53% of 12,191 servers with a package

What its tools let an agent do: 13 read · 2 change

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 53 days ago (2026-09-12). The latest release is v0.6.0.
How does ClockNext compare with other MCP servers?
safety score 72/100 (higher than 38% of 48,255 servers); tools 15 (the typical server has 7); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.