Sinch Messaging APIs + MCP by Sinch

# Fix list: Sinch Messaging APIs + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/sinch, the October 2026 research run, assessed 1 October 2026. Grade B, 63.3 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 Sinch Messaging APIs + 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, 50 out of 100, up to 8.8 more on the total

Why it scored 50: The SMS API takes a service-plan Bearer token, and the Conversation API OAuth 2.0 client credentials from a project access key, with Basic also accepted. No per-key scopes found (25 of 30). No read-only mode. The MCP's --tags option can leave out tool groups, but in single-tenant HTTP mode it performs no inbound authentication (0 of 20). Inbound messages are untrusted text. Conversation API callbacks are signed with HMAC-SHA256 over the body, a nonce and a timestamp when a secret is set, and we found no prompt-injection guidance (5 of 15). Message and delivery lookups by API, no audit log found (10 of 15). The trust centre lists ISO 27001, SOC 2 Type II, PCI and HIPAA, and security@sinch.com takes reports. 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. Agent ergonomics, 50 out of 100, up to 8.1 more on the total

Why it scored 50: We didn't confirm page-size or field controls on message lists (10 of 25). Pagination and filters not confirmed (10 of 20). Error responses with codes, and back-off advice for 5xx (15 of 20). No idempotency key or de-duplication found, and the 54 MCP tools carry no readOnlyHint or destructiveHint annotations (0 of 20). Official SDKs in Node, Python, Java and .NET. A send names an app, a recipient, a channel and a message object (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. 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 SMS prices are published per sender type, and other countries and WhatsApp through a country selector without a login (20). Trial credit of 2 units of local currency and a test number, no card, per the 30 September check (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.

## 4. Reliability, 73 out of 100, up to 5.4 more on the total

Why it scored 73: Statuspage at status.sinch.com with components and history (20). IsDown counts 106 incidents across Sinch in 90 days, 3 major and mostly carrier delivery problems. One major was calling in AP-Southeast-1 and we couldn't tie the other two to the SMS or Conversation APIs, so minor only. A 10DLC campaign provisioning degradation ran for about 3 hours 43 minutes on 1 October without stopping sends (20). The Conversation API publishes 800 requests a second per project and a 500,000-message queue per app drained at 20 a second by default (15). Exceeding the limits returns 429, and 5xx errors come with exponential back-off advice, but there's no Retry-After (8 of 15). No SLA found (0). The SMS and Conversation APIs are generally available. The MCP server is a developer preview (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, 81 out of 100, up to 3.1 more on the total

Why it scored 81: OpenAPI YAML for the Conversation API, linked from its reference page (25). llms.txt with Markdown pages (10). Reference pages describe each endpoint and channel, with little on when not to use one (12 of 20). Typed JSON with message types per channel, not checked for enums (10 of 15). Examples and error codes in the references (12 of 15). /v1 paths and Conversation release notes, with no versioning policy found (12 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. 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 general terms. The contracting Sinch entity is named only in the order form (15). Privacy notice, a DPA addendum, a sub-processor list and deletion on request, with no retention periods found (20 of 30). The Template Management API v1 reference gives the date it stopped working, 2026-01-31, but we found no general deprecation policy (10 of 20). Sub-processor list published, and we didn't confirm it gives locations (10 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)

## 7. Maintenance & community, 83 out of 100, up to 1.5 more on the total

Why it scored 83: sinch-sdk-python v2.2.0 tagged on 2026-09-21, and the listing records a release on 2026-09-23 (30). sinch-sdk-java v2.1.1 (2026-07-21) and v2.2.0 (2026-09-17) and sinch-sdk-python v2.2.0 in the last 90 days (20). Closed service with Conversation release notes. The MCP repo had commits through 2026-09-29, but its npm package is still 0.0.1-alpha.6 from 2026-04-14 (10 of 15). Official SDKs current in Node, Python and Java (15). The MCP repo runs lint, build and tests in CI (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.

- Which two Sinch incidents IsDown marked major besides the AP-Southeast-1 calling incident
- Whether the SMS API has an OpenAPI spec too. We didn't load the Conversation YAML itself
- Which SDK release the listing's lastRelease of 2026-09-23 refers to
- The listing had no openapi value. We've patched in the Conversation API YAML linked from its reference page

## Weaknesses

- The MCP server is a developer preview whose npm release dates from 2026-04-14
- 54 MCP tools with no readOnlyHint or destructiveHint annotations
- Separate credential schemes for the SMS, Conversation and Verification APIs, none with scopes
- No SLA, and no Retry-After on 429
- 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.

- Load the MCP with `--tags` for the channels you need, or all 54 tools land in context
- Keep a single-tenant HTTP MCP bound to localhost, it does no inbound authentication
- Expect sends to drain at 20 messages a second per app unless Sinch raises it
- Verify `x-sinch-webhook-signature` against the raw body before parsing the JSON
- Use the regional base URL (us, eu or br) that matches the project

## What the review panel asked for

- Itemise carrier fees
- Publish a rate table
- Add idempotency keys
- 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.