Twilio Programmable Voice API + MCP by Twilio

# Fix list: Twilio Programmable Voice API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/twilio-voice, the October 2026 research run, assessed 1 October 2026. Grade A, 80.4 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 Twilio Programmable 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. Payments & pricing, 40 out of 100, up to 7.5 more on the total

Why it scored 40: No x402, MPP or L402 (0). US per-minute rates for calls, numbers, Media Streams, ConversationRelay, recording and SIP published without a login (20). Free trial without a card, with free units including 75 voice minutes for 30 days (20). A person has to sign up in a browser and verify a phone number (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.

## 2. Agent ergonomics, 80 out of 100, up to 3.3 more on the total

Why it scored 80: List resources take PageSize and return next_page_uri, with no field selection (15 of 25). The Calls list filters by To, From, Status, StartTime and ParentCallSid (20). Numbered error codes with causes and fixes an agent can act on (20). No idempotency key on call creation. The docs say a 429 is safe to retry, and webhooks carry an I-Twilio-Idempotency-Token for de-duplication (10 of 20). A call needs only To, From and a Url or inline Twiml, and official SDKs exist in seven languages (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.

## 3. Security & auth, 85 out of 100, up to 2.6 more on the total

Why it scored 85: API keys come as standard, main or restricted, and restricted keys take up to 100 endpoint permissions each, revocable in the console or by API. No documented option to send a secret in a query string (30). Restricted keys can leave out endpoints such as call recordings, but no MCP has a confirmation step for dialling or buying numbers (15 of 20). Calls carry untrusted caller speech. Webhooks and Media Streams or ConversationRelay websockets are signed with X-Twilio-Signature, and the MCP README warns about injection from untrusted servers (10 of 15). The Monitor Events API keeps an audit trail of account changes, and every call has a log resource (15). Vulnerability disclosure programme page, a HackerOne bug bounty, SOC 2 Type II and ISO 27001, 27017 and 27018. No security.txt (twilio.com/.well-known/security.txt returns 404), and we didn't check for public advisories (15 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. Reliability, 90 out of 100, up to 2 more on the total

Why it scored 90: Status page at status.twilio.com with per-product and per-carrier components (20). IsDown counts 528 incidents across all Twilio products in the last 90 days, 2 of them major. The ones we could read were single-carrier or single-country routes, such as voice failures to DigiMobil Spain on 1 October, and we couldn't tie either major to Programmable Voice, so minor only (20). Outbound calls are limited to 1 call a second per account by default, and Elastic SIP Trunking to 1 a second per trunk per region (15). The REST best-practices page says a 429 means the request wasn't processed and can be retried, with exponential backoff (15). The Twilio APIs SLA commits 99.95 per cent to all paying customers, 99.99 per cent on Administration or Enterprise Edition, with a 10 per cent credit (10). Programmable Voice 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. Transparency & trust, 81 out of 100, up to 1.7 more on the total

Made of editorial 72, provenance 90.

Why it scored 81: Closed service with clear terms, Twilio Inc. or Twilio Ireland Limited by region. SDKs are MIT (15). Privacy notice, a DPA and a sub-processor list with change notifications. Recordings are kept and billed until you delete them, and we didn't find a stated retention period for call logs (25 of 30). Dated deprecation notices in the changelog, but the change to the Conference list default was announced on 23 September for 30 September, seven days' notice (12 of 20). Sub-processors listed with processing locations, and Regional Twilio stores customer content in Ireland or Australia (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. Schema & documentation, 92 out of 100, up to 1.3 more on the total

Why it scored 92: Public OpenAPI specs in the twilio-oai repository, including api_v2010 for calls (25). llms.txt with Markdown twins of the docs, and a hosted docs MCP that searches over 1,800 endpoints (10). The API reference and TwiML pages say when to use Stream for raw audio and ConversationRelay for text only (15 of 20). Typed parameters with enums from the spec, though calls take form-encoded fields (12 of 15). Code samples in every SDK language and a numbered error and warning dictionary (15). API version in the path (2010-04-01) and a public changelog with dated voice entries in September 2026 (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, 85 out of 100, up to 1.3 more on the total

Why it scored 85: twilio-node 6.1.2 tagged on 2026-09-28 (30). Releases 6.1.0, 6.1.1 and 6.1.2 in the last 90 days, plus ten changelog entries in September 2026 (20). Closed service with a public changelog and paid support. The twilio-labs/mcp repo has 12 open issues and 12 open pull requests, and the alpha package was last published in July 2025 (10 of 15). Official SDKs current in seven languages (15). twilio-node needs Node 20 or later, so dependencies are current (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.

- Which two Twilio incidents IsDown marked major in the last 90 days, and whether either touched Programmable Voice
- Whether the self-serve CPS ceiling (30 in the listing) and 24-hour queue still hold, since the CPS glossary we read didn't state them

## Weaknesses

- US outbound at $0.014 a minute, plus $0.0044 for Media Streams or $0.07 for ConversationRelay
- 1 outbound call a second per account by default
- No idempotency key on call creation
- The MCP that can place calls is an alpha last published in July 2025, and the hosted one only searches docs
- No security.txt on twilio.com

## 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.

- Use `<Connect><Stream>` for two-way audio. It blocks further TwiML until the websocket closes
- Use `<Connect><ConversationRelay>` when you only want to handle text, and set `interruptible` for barge-in
- Trial calls reach only verified numbers in your sign-up country
- Retry a 429 with backoff, but check the Calls list before retrying a create that timed out, since there's no idempotency key
- Validate `X-Twilio-Signature` on every webhook and websocket upgrade

## What the review panel asked for

- Document production steps
- Idempotency key on create
- Recording retention setting
- removals saved for major releases
- defaults changed only with a new API version
- Split llms.txt into per-product files
- source the CPS ceiling
- publish call log retention
- confirmation before dialling
- default recording expiry
- Add an idempotency key to call creation
- Add an idempotency key on calls
- Document Retry-After on 429s

## 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.