# Fix list: Voximplant From Anchor Terminal's listing at https://www.anchorterminal.com/tools/voximplant, the October 2026 research run, assessed 1 October 2026. Grade D, 51.9 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 Voximplant: 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. Security & auth, 40 out of 100, up to 10.5 more on the total Why it scored 40: Service accounts sign RS256 JWTs that live up to 1 hour, and each service account gets one or more roles, such as Scenarios. That earns 30, less 10 because the listing's source documents an account ID and API key in the query string as an option (20). Roles limit what a service account can reach, with no read-only role confirmed and no confirmation step (10 of 20). Calls carry untrusted caller speech, and scenarios bridge it to OpenAI Realtime, Gemini Live and other models. No prompt-injection guidance found (0 of 15). Call history by API (10 of 15). No security.txt, bug bounty, disclosure policy or certifications found (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. ## 2. Payments & pricing, 25 out of 100, up to 9.4 more on the total Why it scored 25: No x402, MPP or L402 (0). Per-country per-minute rates, number fees, streaming and connector prices published without a login (20). Signup for a developer account is free, but the pricing page states no trial credit or card policy (5 of 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. Agent ergonomics, 45 out of 100, up to 8.9 more on the total Why it scored 45: List methods such as call history take count and offset. We didn't confirm field controls (10 of 25). Filters not confirmed this run (10 of 20). Management API errors page with codes (15 of 20). No idempotency key or safe-retry guidance found (0). Official Node and Python API clients, but a first call needs an uploaded VoxEngine scenario and a rule before StartScenarios (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. ## 4. Reliability, 65 out of 100, up to 7 more on the total Why it scored 65: Statuspage at status.voximplant.com with components and history (20). Incidents in the history feed since 30 July are regional, PSTN delays in some regions for 46 minutes on 3 September, Russian and Kazakh carrier problems on 24, 28 and 30 September, and outages in the separate Kit product, so minor only (20). Limits are published with numbers, 50 call attempts, 10 unanswered calls and 3 active HTTP requests per session, 1,000 users per account, and a block on destinations above 20 cents a minute (15). No 429 or retry guidance found (0). No SLA found (0). The platform 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. ## 5. Schema & documentation, 71 out of 100, up to 4.7 more on the total Why it scored 71: OpenAPI spec for the Management API at docs.voximplant.ai/openapi.json and .yaml (25). llms.txt with Markdown pages (10). Reference pages describe each Management API method and VoxEngine class, with little on when not to use one (12 of 20). Typed parameters from the spec (12 of 15). A Management API errors page and examples (12 of 15). No public changelog found and no version in the API path (0 of 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. ## 6. Maintenance & community, 50 out of 100, up to 4.4 more on the total Why it scored 50: The listing records a release on 2026-08-26, 36 days ago, which we didn't re-check (20). Release count in the last 90 days not established (5 of 20). No public changelog. Support exists (5 of 15). Official Node and Python API clients (15). Package health not checked (5 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. ## 7. Transparency & trust, 63 out of 100, up to 3.2 more on the total Made of editorial 45, provenance 80. Why it scored 63: Closed service with clear terms, Voximplant, Inc. The API clients are Apache-2.0 (15). The privacy policy states retention (closed accounts deleted within 12 months, billing data kept 7 years), makes a DPA available on request, and mentions subcontractors. Cloud recordings are kept 3 months or sent to your own S3 (25 of 30). No deprecation policy or dated notices found (0). Data may be processed in the US, Europe or elsewhere with an option to keep it in the EU, but there's no named sub-processor list (5 of 20). 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): - Changelog: not found (0 of 10) - security.txt: not found (0 of 10) ## 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. - Whether the query-string API key option is still documented, since the authorisation page we read mentions only service accounts and keys - Whether new accounts get trial credit, and whether a card is needed - The listing had no OpenAPI URL. We've patched it to docs.voximplant.ai/openapi.json and added the openapi tag ## Weaknesses - Scenarios are VoxEngine JavaScript with their own limits (16 MB memory, 1-second callbacks) - US outbound at $0.017 a minute is higher than most here - API key accepted in the query string, and no security.txt - No public changelog, SLA or deprecation policy found - No action MCP server, docs search only ## 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. - Upload a VoxEngine scenario and a rule first, then start it with StartScenarios and pass the number in script_custom_data - Use a service-account JWT rather than api_key in the URL - Give the service account only the roles the agent needs, such as Scenarios - Ask support to lift the 20-cent destination block before calling expensive routes ## What the review panel asked for - State the trial credit - Document 429 and retry behaviour - Publish an SLA ## 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.