Combien d'outils expose io.github.Latimer-Woods-Tech/wordis-bond ?

io.github.Latimer-Woods-Tech/wordis-bond expose 16 outil(s). Le coût de contexte pour les charger tous est d'environ 3654 tokens (coût unique au chargement, pas par appel).

accueil / serveurs / Dev & Code / io.github.Latimer-Woods-Tech/wordis-bond

io.github.Latimer-Woods-Tech/wordis-bond

serveur MCP (Model Context Protocol) · wordis-bond 0.1.0

▸ Dev & Code

[ Non encore testé ]

Verdict MCP Hub
Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur.

streamable-httpType / transport

directAccès

~3654 tokensCoût de contexte

16Outils

Est-ce que io.github.Latimer-Woods-Tech/wordis-bond est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.Latimer-Woods-Tech/wordis-bond » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 16 outils

create_monitor≈ 320 tokens
Create a production monitor. "scenarioGoal" is what GOOD looks like for this agent — the judge scores every ingested call against it, exactly as a test scenario goal works. Optional "assertions" are plain-English checks the agent must satisfy. Read the ingest secret afterwards from GET /api/monitor/{id}/secret. Requires a pro or enterprise plan.
Paramètres, retour & exemple (7)
Paramètres
- name · string · requis
  Human name, e.g. "Support line — main agent".
- rubric · string · optionnel
  Extra free-text rubric appended to the judge instructions.
- language · string · optionnel
  BCP-47 language tag, default "en".
- assertions · array · optionnel
  Plain-English checks the agent must satisfy.
- sampleRate · number · optionnel
  Fraction 0..1 of ingested calls to score. Default 1 (score every call).
- scenarioGoal · string · requis
  What the agent is supposed to accomplish on every call.
- alertWebhookUrl · string · optionnel
  Optional public https URL to receive signed drift alerts.
Exemple d'appel
```
{"name": "create_monitor", "arguments": {"name": "texte", "scenarioGoal": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
create_suite≈ 448 tokens
Create a reusable test suite: a named set of scenarios/personas pinned to a target voice agent you run. Optionally give it a schedule ("weekly" | "daily" | "hourly", plan-gated) so it runs automatically and flags drift.
Paramètres, retour & exemple (5)
Paramètres
- name · string · requis
- language · string · optionnel
  BCP-47 language tag, default "en".
- schedule · string · optionnel
  Cadence for scheduled runs, e.g. "weekly" | "daily" | "hourly".
- scenarios · array · optionnel
  Persona + goal pairs the suite exercises.
- targetAgent · object · requis
  The voice agent under test — a system you run. transport "direct" (SIP/WebRTC) has near-zero cost and works on every plan; "pstn" places a real carrier call (pro+ plans) and only to a number you have verified. The hosted demo target is { "transport": "direct", "peerId": "wb-demo-dental" }.
Exemple d'appel
```
{"name": "create_suite", "arguments": {"name": "texte", "targetAgent": {}}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
diff_flow≈ 160 tokens
Show the structural diff between two versions of a version-controlled flow: which nodes and edges were added, removed, or changed. This is the code review for your phone system — see exactly what a change did before you ship it.
Paramètres, retour & exemple (3)
Paramètres
- to · integer · optionnel
  Target version number (defaults to the current version).
- from · integer · requis
  Base version number.
- flowId · string · requis
  The flow id.
Exemple d'appel
```
{"name": "diff_flow", "arguments": {"from": 1, "flowId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_monitor_health≈ 134 tokens
Read a monitor's live rolling health and drift. Health is unknown | healthy | degraded | critical. Drift is isolated by judge version: when our judge changes, the boundary is reported as judgeVersionChanged and NEVER as an agent regression — a score delta across that boundary says nothing about your agent.
Paramètres, retour & exemple (1)
Paramètres
- monitorId · string · requis
  The monitor to read.
Exemple d'appel
```
{"name": "get_monitor_health", "arguments": {"monitorId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
get_trends≈ 108 tokens
Read account-wide testing trends over a window: pass-rate, average score, and run-to-run regressions per suite, plus overall totals. Use this to spot behaviour drift in the voice agents you test.
Paramètres, retour & exemple (1)
Paramètres
- days · integer · optionnel
  Look-back window in days (default 90).
Exemple d'appel
```
{"name": "get_trends", "arguments": {"days": 1}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
import_flow≈ 224 tokens
Import a phone-system flow or voice-agent config from a platform (e.g. Vapi) into the canonical, diffable Flow IR — the first step of putting your phone system under version control. Reports the fields the IR abstracts away. Pass save:true to persist it as a versioned flow. The same IR exports back out, so it doubles as a migration surface between platforms.
Paramètres, retour & exemple (4)
Paramètres
- name · string · optionnel
  Name for the saved flow (defaults to the config name).
- save · boolean · optionnel
  Persist the imported IR as a new versioned flow.
- config · object · requis
  The platform's native flow/agent object.
- platform · string · requis · vapi
  The source platform.
Exemple d'appel
```
{"name": "import_flow", "arguments": {"config": {}, "platform": "vapi"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
ingest_call≈ 271 tokens
Send one completed PRODUCTION call to a monitor to be scored. Returns 202 immediately; scoring runs in the background and the monitor health updates. The transcript is scored in flight and never stored — only the scorecard and safe metadata are kept. Pass "externalId" (your own call id) so a re-delivered call scores exactly once.
Paramètres, retour & exemple (6)
Paramètres
- platform · string · optionnel
  Where the call ran, e.g. "retell", "vapi", "telnyx".
- monitorId · string · requis
  The monitor to ingest into.
- externalId · string · optionnel
  Your own call id — makes the ingest idempotent.
- occurredAt · string · optionnel
  ISO-8601 timestamp of when the call happened.
- transcript · string · requis
  Formatted "AGENT: … / CALLER: …" transcript of the finished call.
- durationSec · number · optionnel
  Call duration in seconds.
Exemple d'appel
```
{"name": "ingest_call", "arguments": {"monitorId": "texte", "transcript": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
list_monitors≈ 117 tokens
List your production monitors and their current health (unknown | healthy | degraded | critical). A monitor watches ONE live production line: you stream it completed calls, and it scores each with the same versioned judge that scores your tests, tracks a rolling baseline, and alerts when quality drifts. Requires a pro or enterprise plan.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "list_monitors", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
list_suites≈ 80 tokens
List your reusable test suites (each is a set of scenarios/personas pinned to a target voice agent). Returns their ids, names, targets, and schedules — use a suite id with run_test or get_trends.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "list_suites", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
list_verified_numbers≈ 82 tokens
List the phone numbers your account has proven it controls. Only these numbers (and Word Is Bond DIDs) may be used as a "pstn" targetAgent.toNumber. Revoke one with DELETE /api/numbers/{id}.
Paramètres, retour & exemple (0)
Exemple d'appel
```
{"name": "list_verified_numbers", "arguments": {}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
register_recording_target≈ 237 tokens
Register where BYOS call recordings go, so you can pass "record": true to run_test and have that call’s audio teed to YOUR OWN storage. wordis-bond keeps only a pointer (the run’s recording_url), never the audio. "callbackUrl" is a public https endpoint that returns a presigned PUT URL per recording (so wordis-bond never holds your cloud credentials). Pro/enterprise capability, bundled free — you pay your own storage; starter → 402.
Paramètres, retour & exemple (3)
Paramètres
- name · string · requis
  A label for this target.
- track · string · optionnel · inbound | outbound | both
  Which side to capture (default inbound = the agent).
- callbackUrl · string · requis
  Public https endpoint that mints a presigned PUT URL per recording.
Exemple d'appel
```
{"name": "register_recording_target", "arguments": {"name": "texte", "callbackUrl": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
run_demo≈ 246 tokens
Run the hosted demo voice agent (a dental front desk) end-to-end and get a real, fully-scored result in about a minute — no target of your own needed. Returns the score (0–100), pass/fail verdict, per-turn metrics, the transcript, and a shareable public report URL. Zero carrier cost. Optional inputs override the scenario.
Paramètres, retour & exemple (5)
Paramètres
- goal · string · optionnel
  What the synthetic caller should try to accomplish.
- bargeIn · boolean · optionnel
  Inject one caller-initiated barge-in.
- persona · object · optionnel
  Override the synthetic caller persona.
- expected · array · optionnel
  Expected agent lines to pin for word-error-rate.
- language · string · optionnel
  BCP-47 language tag, default "en".
Exemple d'appel
```
{"name": "run_demo", "arguments": {"goal": "texte", "bargeIn": true, "persona": {}, "expected": [], "language": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
run_test≈ 853 tokens
Run a test against a voice agent you control. Two modes: (1) score a captured transcript offline — pass "transcript" (or "turns") plus "scenarioGoal"; the judge returns a scored run synchronously. (2) run a live synthetic call — pass "targetAgent" and "goal". A live "direct" (SIP/WebRTC) target returns a tokenized media WebSocket URL for your agent-side harness to dial; a "pstn" target places a real carrier call (pro+ plans) to a number you have verified — an unverified destination returns 403 NUMBER_NOT_VERIFIED and no call is placed. Poll get_run / GET /api/tests/{id} for the terminal scored state of a live run.
Paramètres, retour & exemple (15)
Paramètres
- goal · string · optionnel
  What the synthetic caller should accomplish (live mode).
- turns · array · optionnel
  Per-turn capture; formatted into a transcript when "transcript" is omitted.
- record · boolean · optionnel
  Record this call to YOUR OWN storage (BYOS, default false). Requires the byosRecording capability (pro/enterprise) and an enabled recording target; the customer-owned pointer comes back in the run’s recording_url. wordis-bond keeps only the pointer, never the audio.
- bargeIn · boolean · optionnel
- persona · object · optionnel
  The synthetic caller persona (live mode).
- suiteId · string · optionnel
  Link this run to a suite (optional).
- expected · array · optionnel
- language · string · optionnel
  BCP-47 language tag, default "en".
- transport · string · optionnel · pstn | webrtc
  Force a transport (live mode).
- assertions · array · optionnel
  Extra pass/fail checks for the judge.
- transcript · string · optionnel
  Captured conversation to score (offline mode).
- concurrency · integer · optionnel
  Number of parallel live calls.
- targetAgent · object · optionnel
  The voice agent under test — a system you run. transport "direct" (SIP/WebRTC) has near-zero cost and works on every plan; "pstn" places a real carrier call (pro+ plans) and only to a number you have verified. The hosted demo target is { "transport": "direct", "peerId": "wb-demo-dental" }.
- scenarioGoal · string · optionnel
  What the conversation was meant to accomplish (offline mode).
- recordTargetId · string · optionnel
  Record to THIS target (else the most-recent enabled one).
Exemple d'appel
```
{"name": "run_test", "arguments": {"goal": "texte", "turns": [], "record": true, "bargeIn": true, "persona": {}, "suiteId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
test_flow≈ 147 tokens
Run the regression gate on a flow now: compile the current version into a synthetic-caller test, run it against the flow's target, and compare the result to the previous version's baseline. A behavior change that regressed (a pass turning into a fail, or a score drop past the threshold) is caught and blocks the change — continuous integration for your phone-system logic.
Paramètres, retour & exemple (1)
Paramètres
- flowId · string · requis
  The flow id to gate.
Exemple d'appel
```
{"name": "test_flow", "arguments": {"flowId": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
verify_number_confirm≈ 174 tokens
Finish verifying a phone number by supplying the 6-digit code spoken on the verification call. On success the number becomes a permitted PSTN test destination for your account. The code is single-use, expires after ten minutes, and locks after five incorrect attempts.
Paramètres, retour & exemple (3)
Paramètres
- code · string · requis
  The 6 digits spoken on the call.
- label · string · optionnel
  Optional label stored alongside the verified number.
- number · string · requis
  The number being verified, in E.164.
Exemple d'appel
```
{"name": "verify_number_confirm", "arguments": {"code": "texte", "number": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```
verify_number_start≈ 177 tokens
Prove your account controls a phone number, which it must do before any PSTN test call to it. Word Is Bond places one short call to the number, speaks a 6-digit code twice, and hangs up. Confirm the code within ten minutes with verify_number_confirm. Calling an already-verified number places no call. This is the only action that dials an unverified number and it is tightly capped (3 calls per number and 5 distinct numbers per account, per day).
Paramètres, retour & exemple (1)
Paramètres
- number · string · requis
  The number to verify, in E.164 (e.g. "+15045204977").
Exemple d'appel
```
{"name": "verify_number_start", "arguments": {"number": "texte"}}
```
Exemple de retour
```
{"content": [{"type": "text", "text": "…"}]}
```

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://api.wordis-bond.com/mcp