# Word Is Bond (remote · api.wordis-bond.com)

Test the voice agents you run: scored transcripts, pass/fail verdicts, latency and WER metrics.

- Trust score: 61/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `api.wordis-bond.com`: 61/100 (this document), [markdown](https://verifymcp.io/servers/latimer-woods-tech-wordis-bond/api.md), [page](https://verifymcp.io/servers/latimer-woods-tech-wordis-bond/api)

## Channel facts

- Endpoint: `https://api.wordis-bond.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 57/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 16 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2414 tokens (~150/item across 16 items; 16 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 95% of tool parameters carry a description.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http latimer-woods-tech-wordis-bond https://api.wordis-bond.com/mcp
```

### Codex

```toml
[mcp_servers.latimer-woods-tech-wordis-bond]
url = "https://api.wordis-bond.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "latimer-woods-tech-wordis-bond": {
      "type": "remote",
      "url": "https://api.wordis-bond.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add latimer-woods-tech-wordis-bond --url https://api.wordis-bond.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  latimer-woods-tech-wordis-bond:
    url: "https://api.wordis-bond.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "latimer-woods-tech-wordis-bond": {
      "type": "http",
      "url": "https://api.wordis-bond.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 60, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 59, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 59, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 58)

First indexed and scored.

## MCP tools (16)

### `run_demo` (~160 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.

Input parameters:

- `bargeIn` (boolean): Inject one caller-initiated barge-in.
- `expected` (array): Expected agent lines to pin for word-error-rate.
- `goal` (string): What the synthetic caller should try to accomplish.
- `language` (string): BCP-47 language tag, default "en".
- `persona` (object): Override the synthetic caller persona.

### `run_test` (~505 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.

Input parameters:

- `assertions` (array): Extra pass/fail checks for the judge.
- `bargeIn` (boolean)
- `concurrency` (integer): Number of parallel live calls.
- `expected` (array)
- `goal` (string): What the synthetic caller should accomplish (live mode).
- `language` (string): BCP-47 language tag, default "en".
- `persona` (object): The synthetic caller persona (live mode).
- `record` (boolean): 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…
- `recordTargetId` (string): Record to THIS target (else the most-recent enabled one).
- `scenarioGoal` (string): What the conversation was meant to accomplish (offline mode).
- `suiteId` (string): Link this run to a suite (optional).
- `targetAgent` (object): 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…
- `transcript` (string): Captured conversation to score (offline mode).
- `transport` (string): Force a transport (live mode).
- `turns` (array): Per-turn capture; formatted into a transcript when "transcript" is omitted.

### `get_trends` (~66 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.

Input parameters:

- `days` (integer): Look-back window in days (default 90).

### `list_suites` (~53 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.

### `create_suite` (~210 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.

Input parameters:

- `language` (string): BCP-47 language tag, default "en".
- `name` (string, required)
- `scenarios` (array): Persona + goal pairs the suite exercises.
- `schedule` (string): Cadence for scheduled runs, e.g. "weekly" | "daily" | "hourly".
- `targetAgent` (object, required): 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…

### `verify_number_start` (~133 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).

Input parameters:

- `number` (string, required): The number to verify, in E.164 (e.g. "+15045204977").

### `verify_number_confirm` (~105 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.

Input parameters:

- `code` (string, required): The 6 digits spoken on the call.
- `label` (string): Optional label stored alongside the verified number.
- `number` (string, required): The number being verified, in E.164.

### `list_verified_numbers` (~57 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}.

### `register_recording_target` (~160 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.

Input parameters:

- `callbackUrl` (string, required): Public https endpoint that mints a presigned PUT URL per recording.
- `name` (string, required): A label for this target.
- `track` (string): Which side to capture (default inbound = the agent).

### `import_flow` (~145 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.

Input parameters:

- `config` (object, required): The platform's native flow/agent object.
- `name` (string): Name for the saved flow (defaults to the config name).
- `platform` (string, required): The source platform.
- `save` (boolean): Persist the imported IR as a new versioned flow.

### `diff_flow` (~91 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.

Input parameters:

- `flowId` (string, required): The flow id.
- `from` (integer, required): Base version number.
- `to` (integer): Target version number (defaults to the current version).

### `test_flow` (~97 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.

Input parameters:

- `flowId` (string, required): The flow id to gate.

### `list_monitors` (~74 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.

### `create_monitor` (~210 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.

Input parameters:

- `alertWebhookUrl` (string): Optional public https URL to receive signed drift alerts.
- `assertions` (array): Plain-English checks the agent must satisfy.
- `language` (string): BCP-47 language tag, default "en".
- `name` (string, required): Human name, e.g. "Support line — main agent".
- `rubric` (string): Extra free-text rubric appended to the judge instructions.
- `sampleRate` (number): Fraction 0..1 of ingested calls to score. Default 1 (score every call).
- `scenarioGoal` (string, required): What the agent is supposed to accomplish on every call.

### `ingest_call` (~192 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.

Input parameters:

- `durationSec` (number): Call duration in seconds.
- `externalId` (string): Your own call id — makes the ingest idempotent.
- `monitorId` (string, required): The monitor to ingest into.
- `occurredAt` (string): ISO-8601 timestamp of when the call happened.
- `platform` (string): Where the call ran, e.g. "retell", "vapi", "telnyx".
- `transcript` (string, required): Formatted "AGENT: … / CALLER: …" transcript of the finished call.

### `get_monitor_health` (~80 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.

Input parameters:

- `monitorId` (string, required): The monitor to read.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/latimer-woods-tech-wordis-bond/api#diagnostics

## Score history

- 2026-08-03: 61
- 2026-08-02: 60
- 2026-08-01: 60
- 2026-07-31: 60
- 2026-07-30: 59
- 2026-07-29: 60
- 2026-07-28: 60
- 2026-07-27: 59
- 2026-07-26: 58

## Links

- Remote endpoint: https://api.wordis-bond.com/mcp
- Repository: https://github.com/Latimer-Woods-Tech/wordis-bond
- Website: https://wordis-bond.com/
- Changelog RSS feed: https://verifymcp.io/servers/latimer-woods-tech-wordis-bond/api/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/latimer-woods-tech-wordis-bond/api/changelog.json
- HTML version of this page: https://verifymcp.io/servers/latimer-woods-tech-wordis-bond/api