# com.openwakeword/wake-word-training

Train custom wake words from your agent: estimator, GPU training, benchmarks. Card or crypto.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.0
- **Author:** com.openwakeword
- **License:** Unknown
- **Endpoints:** streamable-http https://openwakeword.com/mcp
- **Source:** https://openwakeword.com/agents
- **Endpoint health:** reachable (last checked 2026-09-26T21:35:33.239Z, 5 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 4 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-26T21:35:33.239Z
- **Version scanned:** live
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.
**Findings**
- injection-shaped content (note) in the `create_training_job` tool: Imperative addressed to the AI model

## Tools

13 declared. Observed from a live `tools/list` probe.
- `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
- `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 (
- `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 plat
- `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 
- `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: "st
- `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
- `get_training_job` — Job status: awaiting_payment -> paid -> submitted -> completed (or failed/expired). Poll every 60-120s after paying. When completed, includes benchmark results 
- `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 h
- `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 p
- `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 suppor
- `get_commercial_license` — License status; when completed, returns the official license_id and certificate PDF URL.

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"wake-word-training\": {\n      \"type\": \"http\",\n      \"url\": \"https://openwakeword.com/mcp\"\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/com.openwakeword%2Fwake-word-training
- Install plan: https://forgeregistry.com/api/v1/packages/com.openwakeword%2Fwake-word-training/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/com.openwakeword%2Fwake-word-training
- HTML page: https://forgeregistry.com/registry/com.openwakeword%2Fwake-word-training
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.