# Fix list: Telnyx API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/telnyx, the October 2026 research run, assessed 1 October 2026. Grade BB, 73.8 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 Telnyx 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. Security & auth, 45 out of 100, up to 9.6 more on the total Why it scored 45: Bearer API keys created and revoked in the portal, with no per-key scopes found. Claude connectors can authorise through the portal instead (20). No read-only key mode found, and the hosted MCP's invoke_api_endpoint can send messages or buy numbers with no confirmation step (0 of 20). Inbound SMS and WhatsApp bodies are untrusted text. Messaging webhooks are signed, and we found no prompt-injection guidance (5 of 15). Message and detail records by API, with no account audit log found (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. No security.txt or bug bounty found (10 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, 65 out of 100, up to 4.4 more on the total Why 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 message, and per-payment limits aren't published (25 of 40). Per-part SMS and MMS rates and carrier passthrough fees are 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, mint a key at /v2/api_keys and fund the account by x402 or MPP with no browser (20). 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. Reliability, 80 out of 100, up to 4 more on the total Why it scored 80: Statuspage at status.telnyx.com with a readable incident feed (20). One incident hit the API broadly in the last 90 days, intermittent 5XX responses across endpoints for about 2 hours on 23 September, which Telnyx marked major. Telnyx also marked MMS delays to AT&T major (about 3 hours the same day), which we count as a single-carrier route, and logged minor messaging incidents including outbound latency for about 16 hours from 15 September and delays for some outbound messages from 2 to 11 September (10). Limits per the 30 September check are 50 SMS a second and 100 API requests a second on pay-as-you-go (15). The rate-limiting page documents 429 with error 10011, Retry-After and x-ratelimit headers, exponential backoff with jitter, and retrying only safely repeatable calls (15). The SLA file at telnyx.com/ai/sla.json states 99.99 per cent for core voice and messaging with service credits, without saying who qualifies (10). Messaging 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. ## 4. Agent ergonomics, 80 out of 100, up to 3.3 more on the total Why it scored 80: List endpoints take page size and number, with no field selection. The hosted MCP keeps the tool list to 3 meta-tools that load schemas on demand, but we scored the API (15 of 25). Filters on message and number lists (20). JSON errors with a code, title and detail, and a documented code list (20). No idempotency key on message sends found. The rate-limit page says to retry only safely repeatable operations (10 of 20). A send needs from or a messaging profile, to and text. Official SDKs in Node, Python and more (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, 73 out of 100, up to 2.4 more on the total Made of editorial 55, provenance 90. Why it scored 73: Closed service with clear terms (15). Privacy policy covering retention, a Telnyx DPA referenced from the sub-processor page, and about 50 sub-processors. We didn't find stated retention periods for message records (25 of 30). No deprecation policy or dated deprecation notices found (0 of 20). Each sub-processor is listed with its entity, address, products and data categories, with change alerts (15 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): - security.txt: not found (0 of 10) ## 6. Maintenance & community, 83 out of 100, up to 1.5 more on the total Why it scored 83: telnyx-node v7.24.0 and telnyx-python v4.182.0 both tagged on 2026-09-25 (30). 19 telnyx-node tags in the last 90 days (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). 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. Schema & documentation, 93 out of 100, up to 1.1 more on the total Why it scored 93: Public OpenAPI 3 spec in the team-telnyx/openapi repository (25). llms.txt on developers.telnyx.com and telnyx.com, Markdown doc pages and a pricing.md (10). One reference page per endpoint with purpose and parameters, with little on when not to use one (15 of 20). Typed JSON bodies with enums (13 of 15). Request examples and a page of API error codes (15). Versioned /v2 path and public release notes (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. ## 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. - Who qualifies for the 99.99 per cent SLA in telnyx.com/ai/sla.json - The 50 SMS a second and 100 requests a second limits, which we took from the 30 September check - Whether the x402 endpoint returns a 402 challenge and what limits apply (not tested) - The listing's x402 field said unsupported. We've patched it to partial, with tags, details and pricingNotes to match ## Weaknesses - No per-key scopes or read-only keys, and the MCP can send or buy numbers without confirmation - No free credit, a new account starts at zero - API-wide 5XX errors for about 2 hours on 2026-09-23, plus messaging latency and delivery incidents through September - x402 and MPP only top up account credit, they don't pay per message - No security.txt or bug bounty found ## 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. - Register the 10DLC brand ($4.50) and campaign ($10 a month) before sending US long code traffic - Back off on error 10011 for as long as the Retry-After header says - Call get_api_endpoint_schema before invoke_api_endpoint, the schemas aren't in the tool list - Give each agent its own key, since keys can't be scoped - Verify the signature on inbound message webhooks before acting on the text ## What the review panel asked for - Publish top-up limits - Accept x402 per message - State SLA eligibility - Add idempotency keys ## 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.