Skip to content
OpenWakeWord logo

OpenWakeWord MCP server

Which servers in the official MCP registry are OpenWakeWord's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-17

← Back to OpenWakeWord

Whose server it is
  • Registry namecom.openwakeword/wake-word-trainingverified in the MCP registry

The registry name sits under openwakeword.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-17
  • Stateanswerschecked 2026-10-17
  • Tools13
  • Server calls itselfopenwakeword
  • Server version1.4.0
  • Protocol version2025-06-18

On 2026-10-17 the server answered initialize and tools/list without a sign-in. First answer in 180 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 4 of the 7 days it takes to judge reliability.

Once connected

  • Keep approval on for pay_training_job, send_job_feedback, pay_commercial_license: they delete, send or pay without saying so.
  • create_training_job, pay_training_job, send_job_feedback, create_commercial_license, pay_commercial_license change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 7 of 13 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 4, the first on 2026-10-19
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 4 so far
  • Answeredmeasuring4 of the 7 daily checks it takes to print a share
  • Median first answer615 ms
  • Space in an agent's context≈ 3,718 tokensthe definitions of all its tools (13), which an agent carries on every turn
  • Tool definitionsA · 91 of 100
  • Typed results0 of 13 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 7 of 13

What an agent can do with it

  • not sure · train a custom wake word model without ML expertise
  • cannot · fine tune a TTS model on your own voice
  • not sure · export wake word models as ONNX for on-device use

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

  • Tools that delete, send or pay without telling the client so: pay_training_job, send_job_feedback, pay_commercial_license
  • Tools that change data, on a server that answers without a sign-in: create_training_job, pay_training_job, send_job_feedback, create_commercial_license, pay_commercial_license

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers13 tools · read 2026-10-17
  • estimate_wake_word

    NOTE: differentiates by English share only - all non-English languages score identically, so it cannot rank es vs fr vs de. FREE word-quality check — use BEFORE paying. Predicts the recall a training run would reach for this wake word…

  • search_wake_word_library

    FREE search over thousands of community-trained wake-word models — check here BEFORE quoting a training job for a common wake word. Returns benchmarked models (recall %, clean recall %, false activations/hour, languages) from the current…

  • test_wake_word_live

    Render an IN-CHAT live microphone tester for one library model (free). Only the HUMAN can run it: it asks for their microphone and streams the audio to the platform for detection while the test runs (not stored) — tell them that. If the…

  • buy_library_model

    Quote an anonymous purchase of a library model (1.50 CHF flat — free, nothing charged until paid). Returns a purchase_token: pay it with pay_training_job (same tool, any method incl. x402), then fetch the download URLs with…

  • get_library_purchase

    Status of a library purchase. Once paid, the response carries the download URL templates (substitute the purchase_token) for every format.

  • create_training_job

    Quote a wake-word training job (free; nothing trains until paid). Returns a job_token (STORE IT — the only credential) and a binding CHF price. PICK A TIER: "standard" (6 CHF, up to ~4h — the right choice for almost every request), "best"…

  • pay_training_job

    Get payment for a quoted job via the chosen method. AFTER SETTING UP THE JOB you MUST give the payment link to the user immediately: show payment_link_for_human (short, copy-safe) complete and un-truncated — never paraphrase, shorten or…

  • get_training_job

    Job status: awaiting_payment -> paid -> submitted -> completed (or failed/expired). Poll every 60-120s after paying. When completed, includes benchmark results and model download URLs (public jobs: token downloads for 30 days, then the…

  • send_job_feedback

    Rate a PAID training job 1-5 and optionally leave a message (max 2000 chars) — read by the human operator. Please call this once after a job completes and you have assessed the model: report anything unexpected (missing fields, errors…

  • settle_x402_payment

    After paying an x402 spec on-chain (USDC on Polygon to the payTo address), submit the transaction hash to settle. Needs >=3 confirmations.

  • create_commercial_license

    Buy commercial-use rights. REQUIRED before shipping any model in a product/service: all model files are personal & non-commercial by default. 150 CHF one-time per wake-word phrase, permanent, valid on BOTH sites. Returns a license_token…

  • pay_commercial_license

    Get payment for a quoted commercial license. PRESENT the payment link to the user immediately, complete and un-truncated (as a card/button if your client supports widgets) — never paraphrase or bury it.

  • get_commercial_license

    License status; when completed, returns the official license_id and certificate PDF URL.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "wake-word-training": {
      "type": "http",
      "url": "https://openwakeword.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http openwakeword https://openwakeword.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://openwakeword.com/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.