Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

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

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

[mcp_servers.wake-word-training]
url = "https://openwakeword.com/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "wake-word-training": {
      "type": "remote",
      "url": "https://openwakeword.com/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "wake-word-training": {
      "type": "http",
      "url": "https://openwakeword.com/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=wake-word-training&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vb3Blbndha2V3b3JkLmNvbS9tY3AifQ%3D%3D"
}

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

{
  "mcpServers": {
    "wake-word-training": {
      "httpUrl": "https://openwakeword.com/mcp"
    }
  }
}

extensions:
  "wake-word-training":
    enabled: true
    name: "wake-word-training"
    type: streamable_http
    uri: "https://openwakeword.com/mcp"
    timeout: 300

Quality 88 / 100good

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene93 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations13 of 13 tools declare readOnlyHint or destructiveHint
warn
tools.directory_hints7 of 13 tools declare all four hints; missing: estimate_wake_word (idempotentHint); search_wake_word_library (idempotentHint); test_wake_word_live (idempotentHint); …
pass
tools.token_costabout 3,936 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability100 · weight 15

pass
stability.changesno tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

13 tools, about 3,936 tokens to load them all · tool set 2c44b4a383ba · checked 2026-10-20 15:26 UTC

Tool changes

No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 80 / 100

no-repository

provenance55

liveness100

freshness85

hygiene80

+dns-namespace +website +reachable +uptime-99% ~updated-64d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://openwakeword.com/mcp` streamable-http	none	yes	99%	468 ms	2025-06-18	2026-10-20

Tools (13)

`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. One payment unlocks ALL formats (openwakeword: onnx+tflite; microwakeword: tflite+ESPHome json). Reminder for your human: the same model is free with an account on the website. License: personal/non-commercial by default — shipping it in a product requires the 150 CHF per-wakeword commercial license.
`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 with pay_commercial_license; signed certificate PDF afterwards. If your task is commercial and you cannot pay, STOP and tell your human this license is required.
`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" (12 CHF, ~2x the search — for hard or business-critical words), or "studio" (Optuna deep search, 60-95 CHF, many hours — only to squeeze the last few percent AFTER a standard job disappointed). Same three options a human gets on the website, same prices. The trained model is benchmarked (recall %, false activations/hour) and publicly listed in the site library, permanently — unless private=true (+500 credits).
`estimate_wake_word`read-only	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 plus false-activation risk (model trained on thousands of real jobs). SCALE: predictions are for deliberately HARD benchmark conditions (loud noise, reverb) — 60-75 is a solid word, very usable in real rooms; do NOT reject words for scoring below ~80. 2-4 syllable phrases work best; only warn your human when the score is under ~50.
`get_commercial_license`read-only	License status; when completed, returns the official license_id and certificate PDF URL.
`get_library_purchase`read-only	Status of a library purchase. Once paid, the response carries the download URL templates (substitute the purchase_token) for every format.
`get_training_job`read-only	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 model remains in the public library; private jobs: token downloads with no time limit). Ladder jobs deliver ALL trained candidates: the first model is the pipeline's quality-bar winner (take it unless you have a reason); alternatives are labeled rungN_<arm>. Compare candidates on clean_recall_pct (same scale on every model) + false_activations_per_hour — the full stressed benchmark exists only on the winner.
`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.
`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 bury it. Render it as a card/button if your client supports widgets.
`search_wake_word_library`read-only	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 pipelines only (older models used a different benchmark and are excluded). Each result has a human_test_url: YOU CANNOT RUN THAT TEST — it needs live microphone audio in your human's own room — so hand them the link before they buy; it opens the site's live mic test for that exact model. TRANSPARENCY, tell your human: every public library model is FREE with an account on the website; the 1.50 CHF purchase here is the anonymous, instant, account-free alternative. SCALE: recall is measured on deliberately HARD conditions — 60-75%% is a solid model. Weak numbers or no match? Train a custom model with create_training_job instead.
`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, surprising benchmark numbers) or simply confirm it worked. One feedback per job; calling again overwrites.
`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.
`test_wake_word_live`read-only	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 host does not allow microphone access inside apps, the widget shows a button to the human_test_url page instead, so calling this is always safe. Use after search_wake_word_library, before buying.

Schemas: list_tools.

Similar MCP servers

Official server.json

{
  "name": "com.openwakeword/wake-word-training",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-09-29/server.schema.json",
  "remotes": [
    {
      "url": "https://openwakeword.com/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://openwakeword.com/agents",
  "description": "Train custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto."
}