MCP server that wraps the Dagster GraphQL API — manage runs, assets, schedules, sensors, and backfills from any MCP client
Nothing to run from here
Wake Word Training is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
13
tools declared
remote
at its publisher
—
calls last 7d
What it does
Train custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http wake-word-training-mcp https://openwakeword.com/mcp
# 2 — ask your agent for something these tools do
# estimate_wake_word, search_wake_word_library, test_wake_word_live and 10 more
Wake Word Training costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
OPAll 1 server
openwakeword1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http wake-word-training-mcp https://openwakeword.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
13 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
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
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | The wake word phrase, e.g. 'hey aurora' |
| languages | string | no | Optional JSON list like [{"code":"de_DE","percentage":100}] |
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 a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| query | string | yes | Wake word to search for, e.g. 'jarvis' |
| language | string | no | Optional language filter, e.g. 'en_US', 'de_DE'. |
| limit | integer | no | Max results (default 10, max 25). |
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_w
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| model_id | integer | yes | model_id from search_wake_word_library |
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 a
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| model_id | integer | yes | model_id from search_wake_word_library |
Status of a library purchase. Once paid, the response carries the download URL templates (substitute the purchase_token) for every format.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| purchase_token | string | yes | — |
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 AFT
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| wake_word | string | yes | Phrase to detect, e.g. 'hey aurora' |
| tier | string | no | RECOMMENDED — pick one instead of tuning parameters. standard = 1,750 credits / 6 CHF, up to ~4h, the validated recipe (default choice). best = 3,500 credits / 12 CHF, roughly double the search effort |
| languages | array | no | TTS voice mix, e.g. [{"code":"en_US","percentage":100}]. Default English. ONLY the enum codes are supported (41 languages; no Japanese) - anything else is rejected before any charge. Non-English costs |
| training_steps | integer | no | LEGACY (ignored when tier is set). Default 80000 (openwakeword) / 20000 (microwakeword). |
| n_samples | integer | no | Synthetic positives, default 200000 (recommended). |
| augmentation_rounds | integer | no | Default 1 (openwakeword) / 3 (microwakeword). |
| private | boolean | no | +500 credits: model is never listed anywhere and is retrievable ONLY with the job_token, with no time limit (the token is the single key — losing it loses the model). Default false: the model is liste |
| optuna | boolean | no | LEGACY — prefer tier="studio", which works on BOTH engines. PREMIUM deep search, openwakeword only (~48 CHF default vs ~5.4, runs 6-24h): Bayesian search over the full architecture/training space, the |
| optuna_trials | integer | no | Optuna only: Bayesian search trials before the ladder, 5-30 (default 20). Price scales linearly with trials. |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| job_token | string | yes | — |
| method | string | yes | Payment method. 'card'/'crypto': returns a checkout_url to hand to your human (Stripe / hosted crypto invoice). 'crypto_direct': returns a raw pay_address+pay_amount any funded wallet can pay (300+ co |
| pay_currency | string | no | crypto_direct only: coin ticker, default usdcmatic (USDC on Polygon). |
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'
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| job_token | string | yes | — |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| job_token | string | yes | — |
| rating | integer | yes | 1 = bad, 5 = great |
| category | string | no | — |
| message | string | no | Free text, max 2000 chars. |
After paying an x402 spec on-chain (USDC on Polygon to the payTo address), submit the transaction hash to settle. Needs >=3 confirmations.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| engine | string | yes | Target engine. 'openwakeword': desktop / Raspberry Pi / Python (ONNX+TFLite, pip install openwakeword). 'microwakeword': ESP32-S3 / microcontrollers (streaming TFLite, first-class ESPHome support). |
| token | string | yes | The job_token or license_token being paid. |
| tx_hash | string | yes | 0x-prefixed transaction hash |
| kind | string | no | What the token refers to. Default job. |
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 requir
| Parameter | Type | Required | Notes |
|---|---|---|---|
| wake_word | string | yes | — |
| company_name | string | yes | Legal licensee printed on the certificate |
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| license_token | string | yes | — |
| method | string | yes | Payment method. 'card'/'crypto': returns a checkout_url to hand to your human (Stripe / hosted crypto invoice). 'crypto_direct': returns a raw pay_address+pay_amount any funded wallet can pay (300+ co |
| pay_currency | string | no | — |
License status; when completed, returns the official license_id and certificate PDF URL.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| license_token | string | yes | — |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Wake Word Training or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 20 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest1cd9552c30300e75b8af10cebb4d616106f35ef60d3c13b1c3f8664dbeb0cc08
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| estimate_wake_word | no tags | |
| search_wake_word_library | no tags | |
| test_wake_word_live | no tags | |
| buy_library_model | untrusted-inputstate-write | untrusted-input: keyword "fetch"; state-write: declares readOnlyHint: false |
| get_library_purchase | untrusted-input | untrusted-input: keyword "download" |
| create_training_job | state-write | state-write: declares readOnlyHint: false |
| pay_training_job | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_training_job | untrusted-input | untrusted-input: keyword "download" |
| send_job_feedback | state-write | state-write: declares readOnlyHint: false |
| settle_x402_payment | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| create_commercial_license | state-write | state-write: declares readOnlyHint: false |
| pay_commercial_license | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_commercial_license | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest1cd9552c30300e75
Scanned2026-10-20
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Wake Word Training can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.