# Fix list: Vonage Voice API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/vonage-voice, the October 2026 research run, assessed 1 October 2026. Grade C, 59.1 out of 100. This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public. For a coding agent working on Vonage Voice API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published. ## 1. Reliability, 45 out of 100, up to 11 more on the total Why it scored 45: Statuspage at vonageapi.statuspage.io with components and history (20). One major for voice in the last 90 days, a Voice API service issue in the Europe East (eu-4) region for about 2 hours on 20 August. Degraded outbound calls from Australian fixed-line numbers on 16 August we count as single-country and minor (10). No Voice API rate limit on the Voice overview, the OpenAPI document (1.10.0), the API error catalogue or llms.txt; the catalogue gives numbers for Redact and Reports only (0). The catalogue's generic throttling error says to retry after waiting, an amount that differs per API, with no Retry-After or backoff detail (5 of 15). No SLA found, and the API terms page loads only its navigation for our fetcher (0). Voice API is generally available (10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 2. Payments & pricing, 35 out of 100, up to 8.1 more on the total Why it scored 35: No x402, MPP or L402 (0). Per-minute rates are in a downloadable pricing sheet, and the pricing page returns 403 to automated readers (15 of 20). €2 of test credit without a card (20). A person signs up in a browser (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/). - 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which. - 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login. - 20, a free tier or trial that doesn't need a card. - 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API). Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied. Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol. ## 3. Security & auth, 60 out of 100, up to 7 more on the total Why it scored 60: Calls are authorised with an application JWT signed RS256 with the application's private key. Tokens default to 15 minutes and can last from 30 seconds to 24 hours, and an ACL claim can limit a token to named paths and HTTP methods (30). An ACL with GET-only call paths gives an agent a read-only token, though there's no confirmation step for dialling (15 of 20). Calls carry untrusted caller speech. Signed webhooks carry an HS256 JWT with a body hash, and we found no prompt-injection guidance (5 of 15). Call records by GET /v1/calls. No audit log confirmed (10 of 15). No security.txt. `vonage.com/trust-center/` returns 404, trust.vonage.com doesn't resolve and the support knowledge base is closed to our fetcher, so we found no bounty, disclosure policy or certifications (0 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 4. Agent ergonomics, 60 out of 100, up to 6.5 more on the total Why it scored 60: List calls takes page_size from 1 to 100 (default 10) and record_index, with no field selection (15 of 25). Filters on status, date_start, date_end and conversation_uuid, with ordering (20). A shared API error catalogue with codes an agent can look up (15 of 20). No idempotency key or safe-retry guidance found (0). SDKs in Node, Python and four more languages, but the first call needs an application, a private key and a signed JWT (10 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 5. Transparency & trust, 50 out of 100, up to 4.4 more on the total Made of editorial 25, provenance 75. Why it scored 50: Closed service. The API terms set the contracting entity by region in a schedule we couldn't read, since the terms page loads only its navigation for our fetcher (15). Privacy policy names Vonage Holdings Corp. No retention periods, DPA or sub-processor list found on the pages we could read (10 of 30). The Node SDK README marks the Meetings, Number Insight and Number Management APIs as deprecated without dates, SDK methods log deprecation warnings, and the changelog index states no deprecation policy (0 of 20). No sub-processor list or data locations found (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted). The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two. Provenance checks not met in full (half of this category, computed from checked facts): - Endpoint on the vendor's domain: api.nexmo.com is not on vonage.com (0 of 15) - security.txt: not found (0 of 10) ## 6. Schema & documentation, 88 out of 100, up to 2 more on the total Why it scored 88: OpenAPI spec for the Voice API on developer.vonage.com, version 1.10.0 (25). llms.txt that tells agents to keep the api.nexmo.com and rest.nexmo.com hostnames (10). The NCCO reference explains each action, talk, input, record, connect, transfer, with notes on which to choose (14 of 20). Typed fields from the spec (12 of 15). Examples per action, a webhook reference and a shared API error catalogue in RFC 7807 form at developer.vonage.com/en/api-errors, though the Voice spec documents only a 201 for POST /v1/calls (12 of 15). Versioned /v1 path and a public changelog index (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## 7. Maintenance & community, 78 out of 100, up to 1.9 more on the total Why it scored 78: Python SDK 4.9.0 on 16 September 2026, 15 days before the run, and Node SDK 3.30.1 on 8 September (30). Five SDK releases since 3 July, Node 3.29.0, 3.30.0 and 3.30.1 and Python 4.8.2 and 4.9.0 (20). Closed service with a changelog and support site. We didn't sample issue replies, since GitHub's API refused our shell (5 of 15). Official SDKs in six languages, and 3.27.0 added 24 kHz websocket audio (15). CI, lint and PR workflows on the Node SDK, build and mutation-test workflows on the Python SDK (8 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - unchecked: an SLA and the contracting entity by region. The API terms page loads only its navigation for our fetcher - unchecked: certifications and a disclosure programme. `vonage.com/trust-center/` returns 404, trust.vonage.com doesn't resolve, and the support knowledge base is closed to our fetcher by robots.txt - Whether Vonage publishes a Voice API rate limit anywhere. It isn't on the Voice overview, the OpenAPI document (1.10.0), the error catalogue or llms.txt ## Weaknesses - First call needs an application, a private key and a signed JWT - No Voice API rate limit or SLA found, and the error catalogue's throttling advice is to wait an amount that differs per API - Pricing page returns 403 to automated requests, rates live in a spreadsheet - MCP server has no tools for live call control, only a one-way voice message - No security.txt, and the API runs on the legacy nexmo.com domain ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Generate a short-lived JWT with an ACL limited to the call paths the agent needs, and keep the private key out of prompts - Use a `connect` action with a websocket endpoint and `audio/l16;rate=16000` for speech models - Keep the api.nexmo.com hostname, Vonage's llms.txt says not to swap it - Enable signed webhooks and verify the HS256 JWT on each event - Expect RFC 7807 errors (`type`, `title`, `detail`, `instance`) and back off on a throttling error, since no Voice rate limit is published ## What the review panel asked for - Serve prices as plain HTML - Publish Voice API rate limits - Document 429 behaviour ## When it's done Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.