이 MCP로 할 수 있는 일
Tests voice agents and phone-system flows using scored transcripts or live calls, regression suites, production monitors, drift tracking, and performance metrics.
기능
도구
16
도구
create_monitor
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.
입력 스키마
{'type': 'object', 'required': ['name', 'scenarioGoal'], 'properties': {'name': {'type': 'string', 'description': 'Human name, e.g. "Support line — main agent".'}, 'rubric': {'type': 'string', 'description': 'Extra free-text rubric appended to the judge instructions.'}, 'language': {'type': 'string', 'description': 'BCP-47 language tag, default "en".'}, 'assertions': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Plain-English checks the agent must satisfy.'}, 'sampleRate': {'type': 'number', 'description': 'Fraction 0..1 of ingested calls to score. Default 1 (score every call).'}, 'scenarioGoal': {'type': 'string', 'description': 'What the agent is supposed to accomplish on every call.'}, 'alertWebhookUrl': {'type': 'string', 'description': 'Optional public https URL to receive signed drift alerts.'}}, 'additionalProperties': False}
create_suite
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.
입력 스키마
{'type': 'object', 'required': ['name', 'targetAgent'], 'properties': {'name': {'type': 'string'}, 'language': {'type': 'string', 'description': 'BCP-47 language tag, default "en".'}, 'schedule': {'type': 'string', 'description': 'Cadence for scheduled runs, e.g. "weekly" | "daily" | "hourly".'}, 'scenarios': {'type': 'array', 'items': {'type': 'object', 'properties': {'goal': {'type': 'string'}, 'persona': {'description': 'A string, or { name, description }.'}, 'expected': {'type': 'array', 'items': {'type': 'string'}}}}, 'description': 'Persona + goal pairs the suite exercises.'}, 'targetAgent': {'type': 'object', 'required': ['transport'], 'properties': {'peerId': {'type': 'string', 'description': 'Hosted-agent id, e.g. "wb-demo-dental".'}, 'toNumber': {'type': 'string', 'description': 'E.164 number to dial (required for a pstn target). It must be a number this account has proven it controls: verify it first with verify_number_start then verify_number_confirm, otherwise the run is rejected with 403 NUMBER_NOT_VERIFIED and no call is placed.'}, 'transport': {'enum': ['pstn', 'webrtc', 'direct', 'sip'], 'type': 'string'}}, 'description': '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" }.'}}, 'additionalProperties': False}
diff_flow
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.
입력 스키마
{'type': 'object', 'required': ['flowId', 'from'], 'properties': {'to': {'type': 'integer', 'minimum': 1, 'description': 'Target version number (defaults to the current version).'}, 'from': {'type': 'integer', 'minimum': 1, 'description': 'Base version number.'}, 'flowId': {'type': 'string', 'description': 'The flow id.'}}, 'additionalProperties': False}
get_monitor_health
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.
입력 스키마
{'type': 'object', 'required': ['monitorId'], 'properties': {'monitorId': {'type': 'string', 'description': 'The monitor to read.'}}, 'additionalProperties': False}
get_trends
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.
입력 스키마
{'type': 'object', 'properties': {'days': {'type': 'integer', 'maximum': 365, 'minimum': 1, 'description': 'Look-back window in days (default 90).'}}, 'additionalProperties': False}
import_flow
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.
입력 스키마
{'type': 'object', 'required': ['platform', 'config'], 'properties': {'name': {'type': 'string', 'description': 'Name for the saved flow (defaults to the config name).'}, 'save': {'type': 'boolean', 'description': 'Persist the imported IR as a new versioned flow.'}, 'config': {'type': 'object', 'description': "The platform's native flow/agent object."}, 'platform': {'enum': ['vapi'], 'type': 'string', 'description': 'The source platform.'}}, 'additionalProperties': False}
ingest_call
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.
입력 스키마
{'type': 'object', 'required': ['monitorId', 'transcript'], 'properties': {'platform': {'type': 'string', 'description': 'Where the call ran, e.g. "retell", "vapi", "telnyx".'}, 'monitorId': {'type': 'string', 'description': 'The monitor to ingest into.'}, 'externalId': {'type': 'string', 'description': 'Your own call id — makes the ingest idempotent.'}, 'occurredAt': {'type': 'string', 'description': 'ISO-8601 timestamp of when the call happened.'}, 'transcript': {'type': 'string', 'description': 'Formatted "AGENT: … / CALLER: …" transcript of the finished call.'}, 'durationSec': {'type': 'number', 'description': 'Call duration in seconds.'}}, 'additionalProperties': False}
list_monitors
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.
입력 스키마
{'type': 'object', 'properties': {}, 'additionalProperties': False}
list_suites
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.
입력 스키마
{'type': 'object', 'properties': {}, 'additionalProperties': False}
list_verified_numbers
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}.
입력 스키마
{'type': 'object', 'properties': {}, 'additionalProperties': False}
register_recording_target
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.
입력 스키마
{'type': 'object', 'required': ['name', 'callbackUrl'], 'properties': {'name': {'type': 'string', 'description': 'A label for this target.'}, 'track': {'enum': ['inbound', 'outbound', 'both'], 'type': 'string', 'description': 'Which side to capture (default inbound = the agent).'}, 'callbackUrl': {'type': 'string', 'description': 'Public https endpoint that mints a presigned PUT URL per recording.'}}, 'additionalProperties': False}
run_demo
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.
입력 스키마
{'type': 'object', 'properties': {'goal': {'type': 'string', 'description': 'What the synthetic caller should try to accomplish.'}, 'bargeIn': {'type': 'boolean', 'description': 'Inject one caller-initiated barge-in.'}, 'persona': {'type': 'object', 'properties': {'description': {'type': 'string'}}, 'description': 'Override the synthetic caller persona.'}, 'expected': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Expected agent lines to pin for word-error-rate.'}, 'language': {'type': 'string', 'description': 'BCP-47 language tag, default "en".'}}, 'additionalProperties': False}
run_test
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.
입력 스키마
{'type': 'object', 'properties': {'goal': {'type': 'string', 'description': 'What the synthetic caller should accomplish (live mode).'}, 'turns': {'type': 'array', 'items': {'type': 'object', 'properties': {'role': {'enum': ['agent', 'caller'], 'type': 'string'}, 'text': {'type': 'string'}}}, 'description': 'Per-turn capture; formatted into a transcript when "transcript" is omitted.'}, 'record': {'type': 'boolean', 'description': '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': {'type': 'boolean'}, 'persona': {'type': 'object', 'properties': {'name': {'type': 'string'}, 'description': {'type': 'string'}}, 'description': 'The synthetic caller persona (live mode).'}, 'suiteId': {'type': 'string', 'description': 'Link this run to a suite (optional).'}, 'expected': {'type': 'array', 'items': {'type': 'string'}}, 'language': {'type': 'string', 'description': 'BCP-47 language tag, default "en".'}, 'transport': {'enum': ['pstn', 'webrtc'], 'type': 'string', 'description': 'Force a transport (live mode).'}, 'assertions': {'type': 'array', 'items': {'type': 'string'}, 'description': 'Extra pass/fail checks for the judge.'}, 'transcript': {'type': 'string', 'description': 'Captured conversation to score (offline mode).'}, 'concurrency': {'type': 'integer', 'maximum': 25, 'minimum': 1, 'description': 'Number of parallel live calls.'}, 'targetAgent': {'type': 'object', 'required': ['transport'], 'properties': {'peerId': {'type': 'string', 'description': 'Hosted-agent id, e.g. "wb-demo-dental".'}, 'toNumber': {'type': 'string', 'description': 'E.164 number to dial (required for a pstn target). It must be a number this account has proven it controls: verify it first with verify_number_start then verify_number_confirm, otherwise the run is rejected with 403 NUMBER_NOT_VERIFIED and no call is placed.'}, 'transport': {'enum': ['pstn', 'webrtc', 'direct', 'sip'], 'type': 'string'}}, 'description': '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': {'type': 'string', 'description': 'What the conversation was meant to accomplish (offline mode).'}, 'recordTargetId': {'type': 'string', 'description': 'Record to THIS target (else the most-recent enabled one).'}}, 'additionalProperties': False}
test_flow
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.
입력 스키마
{'type': 'object', 'required': ['flowId'], 'properties': {'flowId': {'type': 'string', 'description': 'The flow id to gate.'}}, 'additionalProperties': False}
verify_number_confirm
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.
입력 스키마
{'type': 'object', 'required': ['number', 'code'], 'properties': {'code': {'type': 'string', 'description': 'The 6 digits spoken on the call.'}, 'label': {'type': 'string', 'description': 'Optional label stored alongside the verified number.'}, 'number': {'type': 'string', 'description': 'The number being verified, in E.164.'}}, 'additionalProperties': False}
verify_number_start
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).
입력 스키마
{'type': 'object', 'required': ['number'], 'properties': {'number': {'type': 'string', 'description': 'The number to verify, in E.164 (e.g. "+15045204977").'}}, 'additionalProperties': False}
기록
최근 도구 변경
추가됨
get_monitor_health
2026년 9월 17일 12:43 PM
추가됨
ingest_call
2026년 9월 17일 12:43 PM
추가됨
create_monitor
2026년 9월 17일 12:43 PM
추가됨
list_monitors
2026년 9월 17일 12:43 PM
추가됨
test_flow
2026년 9월 17일 12:42 PM
추가됨
diff_flow
2026년 9월 17일 12:42 PM
추가됨
import_flow
2026년 9월 17일 12:42 PM
추가됨
register_recording_target
2026년 9월 17일 12:42 PM
추가됨
list_verified_numbers
2026년 9월 17일 12:42 PM
추가됨
verify_number_confirm
2026년 9월 17일 12:42 PM
추가됨
verify_number_start
2026년 9월 17일 12:42 PM
추가됨
create_suite
2026년 9월 17일 12:42 PM
추가됨
list_suites
2026년 9월 17일 12:42 PM
추가됨
get_trends
2026년 9월 17일 12:42 PM
추가됨
run_test
2026년 9월 17일 12:42 PM
추가됨
run_demo
2026년 9월 17일 12:42 PM
탐색
유사한 MCP 서버
Andreax
io.github.moralito311-andr/andreax
Offers pay-per-call AI services for inference, agent and workflow design, OCR and transcription, code generation and review, clas…
IA-QA — 130+ QA & Dev Tools for AI Agents
io.github.JcJamet/ia-qa-toolbox
Provides deterministic QA, evaluation, testing, code analysis, prompt and RAG checks, model comparison, and web security diagnost…
CompletionKit
com.completionkit/evals
Runs prompt evaluation workflows over datasets using deterministic checks and LLM judges, with metrics, scoring runs, agreements,…
Replicate
io.github.pipeworx-io/replicate
Provides access to Replicate models, versions, collections, hardware, predictions, and deployments for running and managing hoste…
Huggingface
io.github.pipeworx-io/huggingface
Provides access to Hugging Face model, dataset, and Space metadata, alongside broader structured research and data-routing tools.
Ai Model Experiments
io.github.pipeworx-io/ai-model-experiments
Runs prompts across multiple AI models and compares their outputs, costs, latency, token usage, and errors.
rubrkit
com.rubrkit/rubrkit
Manages AI evaluation artifacts, rubric audits, eval runs, golden cases, proof reports, and drift monitoring for LLM outputs.
Hipocampo MCP
io.github.carrasquelalex1/hipocampo
Provides bilingual semantic memory, embeddings, graph links, code indexing and search, context preload, deduplication, compressio…