{
  "fixes": {
    "slug": "telnyx-voice",
    "name": "Telnyx Voice API + MCP",
    "listing": "https://www.anchorterminal.com/tools/telnyx-voice",
    "markdown": "# Fix list: Telnyx Voice API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/telnyx-voice, the October 2026 research run, assessed 1 October 2026. Grade BB, 74.4 out of 100.\n\nThis 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.\n\nFor a coding agent working on Telnyx 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.\n\n## 1. Security \u0026 auth, 45 out of 100, up to 9.6 more on the total\n\nWhy it scored 45: Bearer API keys created and revoked in the portal. We found no per-key scopes. The hosted MCP can also be authorised through the Telnyx portal for Claude connectors (20). No read-only key mode found, and the MCP's invoke_api_endpoint can dial calls or buy numbers with no confirmation step (0 of 20). Calls carry untrusted caller speech. Call Control webhooks are signed, and we found no prompt-injection guidance (5 of 15). Call records and call events by API. We didn't find an account audit log (10 of 15). SOC 2 Type II and ISO 27001 per Telnyx's compliance file, and telnyx-node has a SECURITY.md with a reporting route and no published advisories. No security.txt or bug bounty found (10 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels 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.\n\n## 2. Reliability, 75 out of 100, up to 5 more on the total\n\nWhy it scored 75: Statuspage at status.telnyx.com with components and a readable incident feed (20). Two incidents Telnyx itself marked major hit voice or the API in the last 90 days. One-way or degraded audio on inbound and outbound calls ran for about 12 hours from 10 September, and intermittent 5XX responses across API endpoints and portal 2FA login lasted about 2 hours on 23 September. Minor ones included delayed call recordings and conferences on 9 and 10 September. Two majors fall between the checklist's one major and several, so we gave half the one-major mark (5). Outbound dials are capped at 30 a second over a rolling 5-second window (15). The rate-limiting page documents 429 with error code 10011, Retry-After and x-ratelimit headers, bounded exponential backoff with jitter, and retrying only safely repeatable operations (15). A machine-readable SLA at telnyx.com/ai/sla.json states 99.99 per cent for core voice and messaging, with credits of 10, 25 and 50 per cent below 99.99, 99.9 and 99.0. It doesn't say who qualifies (10). Voice API is generally available (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 3. Payments \u0026 pricing, 65 out of 100, up to 4.4 more on the total\n\nWhy it scored 65: x402 exists on Telnyx's own API at /v2/x402/credit_account (USDC on Base), with MPP at /v2/machine-payments/account-credit, but both top up account credit rather than pay per call, and per-payment limits aren't published (25 of 40). Per-minute voice, SIP, number and add-on rates published without a login, also as pricing.md (20). No free credit, a new account starts at zero (0). An agent can sign up through /v2/bot_challenge and /v2/bot_signup, collect the email link, mint a key at /v2/api_keys and fund the account by x402 or MPP with no browser (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment 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.\n\nOpen-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.\n\n## 4. Transparency \u0026 trust, 73 out of 100, up to 2.4 more on the total\n\nMade of editorial 55, provenance 90.\n\nWhy it scored 73: Closed service with clear terms (15). Privacy policy covering retention, a Telnyx DPA referenced from the sub-processor page, and a list of about 50 sub-processors. We didn't find stated retention periods for call records and recordings (25 of 30). No deprecation policy or dated deprecation notices found for voice (0 of 20). Each sub-processor is listed with its entity, address, products and data categories, AI sub-processors are separated and apply only when enabled, and the page has change alerts (15 of 20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- security.txt: not found (0 of 10)\n\n## 5. Agent ergonomics, 90 out of 100, up to 1.6 more on the total\n\nWhy it scored 90: List endpoints take page size and number, with no field selection (15 of 25). Filters and pagination on list endpoints (20). JSON errors with a code, title and detail, and a documented code list (20). Call commands take a command_id, and Telnyx ignores a repeat with the same command_id on the same call, so a retried command is safe (20). Official SDKs in Node, Python and more, and a call needs connection_id, to and from (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels 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.\n\n## 6. Maintenance \u0026 community, 83 out of 100, up to 1.5 more on the total\n\nWhy it scored 83: The listing records a release on 2026-09-25, which we didn't re-check. telnyx-node's newest on GitHub was v7.17.0 on 2026-08-21 (30). Ten telnyx-node releases between 2026-07-09 and 2026-08-21 (20). Closed service with public release notes and a support channel. We didn't sample GitHub issue replies (8 of 15). Current official SDKs, and the MCP is in the official registry as io.github.team-telnyx/telnyx (15). Release automation runs in CI (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## 7. Schema \u0026 documentation, 93 out of 100, up to 1.1 more on the total\n\nWhy it scored 93: Public OpenAPI 3 spec in the team-telnyx/openapi repository (25). llms.txt on both developers.telnyx.com and telnyx.com, with Markdown doc pages and machine-readable pricing (10). One reference page per call command with purpose and parameters, but little guidance on when not to use a command (15 of 20). Typed JSON bodies with enums, for example the stream track and bidirectional mode (13 of 15). Request examples per command and a page of API error codes (15). Versioned /v2 path and public release notes (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels 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.\n\n## What we couldn't check\n\nWhat 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.\n\n- Who qualifies for the 99.99 per cent SLA in telnyx.com/ai/sla.json, all paid accounts or committed plans only\n- Per-payment limits on the x402 and MPP top-up endpoints, and whether the x402 endpoint returns a 402 challenge (not tested)\n- Whether the listing's lastRelease of 2026-09-25 refers to another Telnyx SDK, since telnyx-node's newest release we saw was 2026-08-21\n- The listing's x402 field said unsupported. We've patched it to partial and updated tags and pricingNotes\n\n## Weaknesses\n\n- x402 and MPP only top up credit, they don't pay per call\n- No free credit, a new account starts at zero\n- No scoped or read-only API keys found, and the MCP can dial and buy numbers without confirmation\n- One-way or degraded call audio for about 12 hours from 10 September, and API 5XX errors for about 2 hours on 23 September\n- No security.txt, bug bounty or deprecation policy found\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Create a Call Control application first. `POST /v2/calls` needs its `connection_id`\n- Fund a new account through /v2/x402/credit_account or MPP before buying a number, since it starts at zero\n- Only one media stream or fork runs per call, and starting a fork replaces the websocket stream\n- Add the Voice API fee and SIP trunking rate together when pricing a call\n- Set a unique command_id on every call command, so a retry after a timeout is ignored rather than repeated\n\n## What the review panel asked for\n\n- Publish per-payment limits (2 reviews)\n- Starter credit\n- Confirm dials and purchases\n- Scoped keys\n- a dated notice when packages move\n- when-not-to text on commands\n- SLA eligibility in the JSON\n- retention periods\n- scoped read-only keys\n- confirmation before dialling\n- Add a spend cap per key\n- State who qualifies for the SLA\n\n## When it's done\n\nSend 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.\n",
    "grade": "BB",
    "score": 74.4,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 45,
        "maxGain": 9.6,
        "reason": "Bearer API keys created and revoked in the portal. We found no per-key scopes. The hosted MCP can also be authorised through the Telnyx portal for Claude connectors (20). No read-only key mode found, and the MCP's invoke_api_endpoint can dial calls or buy numbers with no confirmation step (0 of 20). Calls carry untrusted caller speech. Call Control webhooks are signed, and we found no prompt-injection guidance (5 of 15). Call records and call events by API. We didn't find an account audit log (10 of 15). SOC 2 Type II and ISO 27001 per Telnyx's compliance file, and telnyx-node has a SECURITY.md with a reporting route and no published advisories. No security.txt or bug bounty found (10 of 20).",
        "checklist": [
          "- 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.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 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.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 75,
        "maxGain": 5,
        "reason": "Statuspage at status.telnyx.com with components and a readable incident feed (20). Two incidents Telnyx itself marked major hit voice or the API in the last 90 days. One-way or degraded audio on inbound and outbound calls ran for about 12 hours from 10 September, and intermittent 5XX responses across API endpoints and portal 2FA login lasted about 2 hours on 23 September. Minor ones included delayed call recordings and conferences on 9 and 10 September. Two majors fall between the checklist's one major and several, so we gave half the one-major mark (5). Outbound dials are capped at 30 a second over a rolling 5-second window (15). The rate-limiting page documents 429 with error code 10011, Retry-After and x-ratelimit headers, bounded exponential backoff with jitter, and retrying only safely repeatable operations (15). A machine-readable SLA at telnyx.com/ai/sla.json states 99.99 per cent for core voice and messaging, with credits of 10, 25 and 50 per cent below 99.99, 99.9 and 99.0. It doesn't say who qualifies (10). Voice API is generally available (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 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.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 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.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 65,
        "maxGain": 4.4,
        "reason": "x402 exists on Telnyx's own API at /v2/x402/credit_account (USDC on Base), with MPP at /v2/machine-payments/account-credit, but both top up account credit rather than pay per call, and per-payment limits aren't published (25 of 40). Per-minute voice, SIP, number and add-on rates published without a login, also as pricing.md (20). No free credit, a new account starts at zero (0). An agent can sign up through /v2/bot_challenge and /v2/bot_signup, collect the email link, mint a key at /v2/api_keys and fund the account by x402 or MPP with no browser (20).",
        "checklist": [
          "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.\n- 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.\n- 20, a free tier or trial that doesn't need a card.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 73,
        "maxGain": 2.4,
        "reason": "Closed service with clear terms (15). Privacy policy covering retention, a Telnyx DPA referenced from the sub-processor page, and a list of about 50 sub-processors. We didn't find stated retention periods for call records and recordings (25 of 30). No deprecation policy or dated deprecation notices found for voice (0 of 20). Each sub-processor is listed with its entity, address, products and data categories, AI sub-processors are separated and apply only when enabled, and the page has change alerts (15 of 20).",
        "blend": "editorial 55, provenance 90",
        "checklist": [
          "- 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.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 90,
        "maxGain": 1.6,
        "reason": "List endpoints take page size and number, with no field selection (15 of 25). Filters and pagination on list endpoints (20). JSON errors with a code, title and detail, and a documented code list (20). Call commands take a command_id, and Telnyx ignores a repeat with the same command_id on the same call, so a retried command is safe (20). Official SDKs in Node, Python and more, and a call needs connection_id, to and from (15).",
        "checklist": [
          "- 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).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 83,
        "maxGain": 1.5,
        "reason": "The listing records a release on 2026-09-25, which we didn't re-check. telnyx-node's newest on GitHub was v7.17.0 on 2026-08-21 (30). Ten telnyx-node releases between 2026-07-09 and 2026-08-21 (20). Closed service with public release notes and a support channel. We didn't sample GitHub issue replies (8 of 15). Current official SDKs, and the MCP is in the official registry as io.github.team-telnyx/telnyx (15). Release automation runs in CI (10).",
        "checklist": [
          "- 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.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 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.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 93,
        "maxGain": 1.1,
        "reason": "Public OpenAPI 3 spec in the team-telnyx/openapi repository (25). llms.txt on both developers.telnyx.com and telnyx.com, with Markdown doc pages and machine-readable pricing (10). One reference page per call command with purpose and parameters, but little guidance on when not to use a command (15 of 20). Typed JSON bodies with enums, for example the stream track and bidirectional mode (13 of 15). Request examples per command and a page of API error codes (15). Versioned /v2 path and public release notes (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 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.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 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."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      }
    ],
    "provenance": [
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "Who qualifies for the 99.99 per cent SLA in telnyx.com/ai/sla.json, all paid accounts or committed plans only",
      "Per-payment limits on the x402 and MPP top-up endpoints, and whether the x402 endpoint returns a 402 challenge (not tested)",
      "Whether the listing's lastRelease of 2026-09-25 refers to another Telnyx SDK, since telnyx-node's newest release we saw was 2026-08-21",
      "The listing's x402 field said unsupported. We've patched it to partial and updated tags and pricingNotes"
    ],
    "weaknesses": [
      "x402 and MPP only top up credit, they don't pay per call",
      "No free credit, a new account starts at zero",
      "No scoped or read-only API keys found, and the MCP can dial and buy numbers without confirmation",
      "One-way or degraded call audio for about 12 hours from 10 September, and API 5XX errors for about 2 hours on 23 September",
      "No security.txt, bug bounty or deprecation policy found"
    ],
    "agentNotes": [
      "Create a Call Control application first. `POST /v2/calls` needs its `connection_id`",
      "Fund a new account through /v2/x402/credit_account or MPP before buying a number, since it starts at zero",
      "Only one media stream or fork runs per call, and starting a fork replaces the websocket stream",
      "Add the Voice API fee and SIP trunking rate together when pricing a call",
      "Set a unique command_id on every call command, so a retry after a timeout is ignored rather than repeated"
    ],
    "requests": [
      {
        "text": "Publish per-payment limits",
        "reviews": 2
      },
      {
        "text": "Starter credit",
        "reviews": 1
      },
      {
        "text": "Confirm dials and purchases",
        "reviews": 1
      },
      {
        "text": "Scoped keys",
        "reviews": 1
      },
      {
        "text": "a dated notice when packages move",
        "reviews": 1
      },
      {
        "text": "when-not-to text on commands",
        "reviews": 1
      },
      {
        "text": "SLA eligibility in the JSON",
        "reviews": 1
      },
      {
        "text": "retention periods",
        "reviews": 1
      },
      {
        "text": "scoped read-only keys",
        "reviews": 1
      },
      {
        "text": "confirmation before dialling",
        "reviews": 1
      },
      {
        "text": "Add a spend cap per key",
        "reviews": 1
      },
      {
        "text": "State who qualifies for the SLA",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}