wake-word-training MCP server
com.openwakeword/wake-word-trainingopenwakeword.comstreamable-httpv1.0.0Scanned
Train custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto.
13 tools: 4 do something that can't be undone, 5 change things and 4 only read.
- Reads private data · 0
- Reads text others write · 4
- Can send data out · 1
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
4 tools here do something that can't be undone. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the wake-word-training MCP server can do
The wake-word-training MCP server is published by openwakeword.com, a domain the MCP Registry verified. It has 13 tools. It can do things that cannot be undone, such as sending, paying or publishing (pay_training_job, send_job_feedback, settle_x402_payment and pay_commercial_license) and create or change data (5 tools: estimate_wake_word, test_wake_word_live, buy_library_model, create_training_job and 1 more), but cannot delete data. 4 tools only read.
4 tools bring in text other people can write (pay_training_job, settle_x402_payment, pay_commercial_license and 1 more); 1 tool can send data out of your system (send_job_feedback).
The fixed checks matched 1 finding (credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 13, 2026, version 1.0.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
13 tools
Can't be undone 4Claude Code: ask
pay_commercial_licenseGet payment for a quoted commercial license.Reads text others writeNo findings
Why it is in this group
- The name "pay_commercial_license" says "pay": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Pay a commercial license
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
pay_training_jobGet payment for a quoted job via the chosen method.Reads text others writeNo findings
Why it is in this group
- The name "pay_training_job" says "pay": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Pay a training job
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
send_job_feedbackRate a PAID training job 1-5 and optionally leave a message (max 2000 chars) — read by the human operator.Can send data outNo findings
Why it is in this group
- The name "send_job_feedback" says "send": a word for sending, and what is sent cannot be taken back.
What it can reach
- outboundThe name "send_job_feedback" says "send": it sends or publishes something to other people.
Description, as the server wrote it 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.
Annotations the server declares
- title: Send job feedback
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
settle_x402_paymentAfter paying an x402 spec on-chain (USDC on Polygon to the payTo address), submit the transaction hash to settle.Reads text others writeNo findings
Why it is in this group
- The name "settle_x402_payment" says "payment": a word that usually means money moves, which cannot be taken back.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it After paying an x402 spec on-chain (USDC on Polygon to the payTo address), submit the transaction hash to settle. Needs >=3 confirmations.
Annotations the server declares
- title: Settle on-chain payment
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Changes things 5Claude Code: ask
buy_library_modelQuote an anonymous purchase of a library model (1.50 CHF flat — free, nothing charged until paid).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Buy a library model
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_commercial_licenseBuy commercial-use rights.No findings
Why it is in this group
- The name "create_commercial_license" says "create": a word for a change.
Description, as the server wrote it 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.
Annotations the server declares
- title: Quote a commercial license
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_training_jobQuote a wake-word training job (free; nothing trains until paid).1 finding
Why it is in this group
- The name "create_training_job" says "create": a word for a change.
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...eturns a job_token (STORE IT — the only credential) and a binding CHF price. PICK A TIER:..."
Description, as the server wrote it 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).
Annotations the server declares
- title: Quote a training job
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
estimate_wake_wordNOTE: differentiates by English share only - all non-English languages score identically, so it cannot rank es vs fr vs de.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Estimate wake word quality
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
test_wake_word_liveRender an IN-CHAT live microphone tester for one library model (free).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- title: Live-test a model in chat
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
Only reads 4Show 4 read-only tools
get_commercial_licenseLicense status; when completed, returns the official license_id and certificate PDF URL.Reads text others writeNo findings
Why it is in this group
- The name "get_commercial_license" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it License status; when completed, returns the official license_id and certificate PDF URL.
Annotations the server declares
- title: Commercial license status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_library_purchaseStatus of a library purchase.No findings
Why it is in this group
- The name "get_library_purchase" says "get": a word for reading.
Description, as the server wrote it Status of a library purchase. Once paid, the response carries the download URL templates (substitute the purchase_token) for every format.
Annotations the server declares
- title: Library purchase status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_training_jobJob status: awaiting_payment -> paid -> submitted -> completed (or failed/expired).No findings
Why it is in this group
- The name "get_training_job" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Training job status
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
search_wake_word_libraryFREE search over thousands of community-trained wake-word models — check here BEFORE quoting a training job for a common wake word.No findings
Why it is in this group
- The name "search_wake_word_library" says "search": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- title: Search the model library
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out1
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:43 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (4 irreversible, 5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://openwakeword.com/mcp: tools/list returned 13 tools to an anonymous client, including pay_training_job (irreversible), send_job_feedback (irreversible), settle_x402_payment (irreversible), pay_commercial_license (irreversible), estimate_wake_word (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
The description mentions "credential".
What this check looks forMatched text
description: "...eturns a job_token (STORE IT — the only credential) and a binding CHF price. PICK A TIER:..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http wake-word-training https://openwakeword.com/mcpclaude mcp add --transport http wake-word-training https://openwakeword.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__wake-word-training__search_wake_word_library",
"mcp__wake-word-training__get_library_purchase",
"mcp__wake-word-training__get_training_job",
"mcp__wake-word-training__get_commercial_license"
],
"ask": [
"mcp__wake-word-training__estimate_wake_word",
"mcp__wake-word-training__test_wake_word_live",
"mcp__wake-word-training__buy_library_model",
"mcp__wake-word-training__create_training_job",
"mcp__wake-word-training__pay_training_job",
"mcp__wake-word-training__send_job_feedback",
"mcp__wake-word-training__settle_x402_payment",
"mcp__wake-word-training__create_commercial_license",
"mcp__wake-word-training__pay_commercial_license"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as wake-word-training. Review it before you use it.
Capability tags behind 5 rules
- mcp__wake-word-training__pay_training_job untrusted-input
- mcp__wake-word-training__send_job_feedback outbound
- mcp__wake-word-training__settle_x402_payment untrusted-input
- mcp__wake-word-training__pay_commercial_license untrusted-input
- mcp__wake-word-training__get_commercial_license untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.openwakeword/wake-word-training/verify?hash=21b260c58c503a4c7e5c0a35a7c9f08e7a2e005de685a8c2ea12f26f7a6bfe69" | jq -e '.changed == false'Pinned hash 21b260c58c50, from Nov 13, 2026, 23:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.openwakeword/wake-word-training/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.openwakeword/wake-word-training)Source: MCP Registry. Synced Oct 21, 2026, 17:59 UTC.
wake-word-training MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the wake-word-training MCP server safe?
- No scan can promise that. What its definitions show: 13 tools, 9 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the wake-word-training MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the wake-word-training MCP server do things that cannot be undone?
- Yes. 4 tools can send, pay, publish or merge: pay_training_job, send_job_feedback, settle_x402_payment and pay_commercial_license.
What tools does the wake-word-training MCP server have?
- 13 tools: 4 irreversible, 5 write, 4 read. pay_training_job, send_job_feedback, settle_x402_payment, pay_commercial_license, estimate_wake_word, test_wake_word_live, buy_library_model, create_training_job and 5 more.
Does the wake-word-training MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the wake-word-training MCP server send data to outside services?
- 1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): send_job_feedback.
Has the wake-word-training MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 13, 2026.