Head to head · Inbound messaging · October 2026 research run

Sendblue vs Wati

Sendblue scores 59.7 (C) on agent readiness against Wati's 51.1 (D), and leads in 6 of 7 scored categories. Wati leads on schema & documentation. Both do inbound messaging.

Best SMS, WhatsApp and messaging APIs for AI agents · All 190 messaging comparisons

Which one, for what

Sendblue C

Best for An agent that answers people over iMessage on a US number, where blue-bubble threads, typing indicators and reactions matter and the person texts first.

Ahead on

  • Reliability, 61 against 55
  • Agent ergonomics, 76 against 48
  • Security & auth, 46 against 40
  • Payments & pricing, 40 against 20
  • Maintenance & community, 72 against 62
  • Transparency & trust, 58 against 52

Also in its favour

  • Runs on your own machine
  • Free to start without a card

Watch for

Proactive outbound messaging needs the Blue Ocean plan, which has no public price. The $100 AI Agent plan is inbound-first

Wati D

Best for Businesses whose customers are on WhatsApp and Instagram and who want an inbox, campaigns and an agent on one account.

Ahead on

  • Schema & documentation, 79 against 66

Watch for

No idempotency keys; the docs say not to assume idempotency and to reconcile before resending

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Agent ergonomics Sendblue +28

Sendblue 76

Message lists take limit from 1 to 100, and the MCP server adds a jq_filter on every tool, a read-only filter and a three-tool dynamic mode (20 of 25). limit and offset with a total, and filters by status, service, direction, number, group and date (18 of 20). Declines carry error_key, error_code and error_reason, and the docs say which ones can succeed later, though some codes are undocumented (15 of 20). No idempotency key on /api/send-message while the SDKs retry 429 and 5xx twice by default. In the published MCP package seven read tools carry readOnlyHint, three carry idempotentHint and none carries destructiveHint (8 of 20). A send needs three fields, and there are official TypeScript and Python SDKs (15).

Wati 48

The MCP catalogue lists 73 WATI tools plus Astra groups, some loaded on demand through list_skills and activate_skill (10 of 25). Page and page size with filters on lists, and bounded search (17 of 20). Error handling is documented per status, but bodies can be JSON, plain text or empty, so an agent can't rely on one shape (10 of 20). No idempotency keys; tag add and remove are idempotent, and the docs say to reconcile rather than retry sends (5 of 20). No official SDK; runnable examples in five languages, and region-specific hosts add setup (6 of 15). 10 + 17 + 10 + 5 + 6 = 48.

Payments & pricing Sendblue +20

Sendblue 40

No x402, MPP or L402 (0). Plan prices are public, $0 and $100 a month per line with no per-message fee, while the outbound plan is priced through sales (10 of 20). The free plan needs no card (20). The CLI creates an account and API keys with no browser, but a person has to text a one-time code from a phone or supply an email code, so half (10 of 20).

Wati 20

No x402, MPP or L402 (0). Public plan prices only, plus Meta's fees by reference (10 of 20). A 7-day free trial whose card rule isn't stated (10 of 20). A person signs up and connects a WhatsApp Business account (0). 0 + 10 + 10 + 0 = 20.

Schema & documentation Wati +13

Sendblue 66

We graded the REST API. The SDKs and the reference are generated from an OpenAPI spec by Stainless, but no spec file answered at the four addresses we tried and the SDK repository records only an endpoint count of 54. The published MCP package has JSON Schema inputs on its 18 tools (12 of 25). llms.txt and a Markdown twin of every docs page at /index.md (10). The reference and llms.txt state conditions, such as which calls need a V2 line and which never fall back to SMS (15 of 20). Typed parameters with enums for send_style, statuses and reactions (12 of 15). Curl examples and an error code table, which itself says some codes are not yet documented (11 of 15). Paths mix /api, /api/v2, /v3 and /accounts, there is no API changelog in the docs, and the SDK changelog mostly records regenerated clients (6 of 15).

Wati 79

No standalone spec file was found, but every reference page embeds the OpenAPI 3.0.4 contract for its operation, with the documentation version 2.6 (20 of 25). llms.txt and Markdown pages (10). Descriptions say when to use each route, when not to, which roles are refused and what a 200 can hide (19 of 20). Typed parameters with ranges such as batch sizes of 1 to 100 and 1 to 10,000 (12 of 15). Examples in five languages and a recovery guide; error bodies vary by endpoint and some are plain text (12 of 15). Versioned documentation and a public roadmap, but no changelog (6 of 15). 20 + 10 + 19 + 12 + 12 + 6 = 79.

Maintenance & community Sendblue +10

Sendblue 72

sendblue on npm is at 3.22.0 per the SDK changelog, dated 30 October 2026, with tags v3.20.0 (9 October), v3.20.1 (17 October), v3.21.0 (22 October), v3.21.1 (23 October) and v3.21.2 (30 October) since the last check. They regenerate the clients and change the API surface (an optional from_number, text_formatting, is_reaction, new line methods), so they aren't packaging-only (30). 20 SDK tags from v3.11.0 (17 August) to v3.21.2 (30 October), counted half as SDK tags, still well over three (20). No API changelog in the docs, support by email, and we couldn't read the GitHub issue trackers (6 of 15). Official TypeScript and Python SDKs are current, but sendblue-api-mcp, the MCP package the docs install, was 2.0.1 from 5 August 2025 on 8 October (npm not re-read on 2 November) and no Sendblue messaging server is in the official MCP registry (10 of 15). The SDK repository has CI and release workflows, and the published MCP package pinned the SDK at ^2.0.1 (6 of 10).

Wati 62

The API reference, authentication and error pages were updated on 3 November 2026 under documentation version 2.6, read as the last published API change (30). No changelog; the MCP registry entry moved to 1.1.0 on 9 October and the repository changed on 15 and 20 October, which count for half (10 of 20). Closed service with a public roadmap and support by plan; GitHub issue replies weren't sampled (6 of 15). io.github.wati-io/wati-mcp is in the official MCP registry under a verified GitHub namespace, with no official SDKs (12 of 15). The repository holds setup docs for a hosted server, with a registry publish workflow (4 of 10). 30 + 10 + 6 + 12 + 4 = 62.

Reliability Sendblue +6

Sendblue 61

Read with the hosted lines. status.sendblue.com is an UptimeRobot page, kept at 20 as awarded on 8 October. Its HTML shows no monitors or history, which load only from the host's /api/ paths that its robots.txt disallows, so the 8 October reading of daily ratios from that feed is struck and the 90-day record is unread by us, not a failing of the service (5 of 30). Rate limits are published with numbers per plan and per line (15). The docs say to slow down or spread traffic on a 429 and to verify state after 504 outcome_unknown, with no Retry-After header documented and an idempotency key only on App Card updates (8 of 15). The API page shows a 99.9% Uptime SLA figure and the docs list custom SLAs for enterprise, but no SLA document was found and the terms disclaim availability (3 of 10). The REST API is generally available (10). 20 + 5 + 15 + 8 + 3 + 10 = 61.

Wati 55

Read with the hosted lines. status.wati.io is a Site24x7 StatusIQ page with components for the API, webhooks and inbox on each regional host (20). Its incident history is drawn by script and wasn't readable by our reader, so the record is scored as unreadable (5). Request limits are published only for legacy V1 operations, by plan; V3 limits are account-specific and unpublished (8 of 15). The docs say to honour Retry-After when present, use bounded backoff and reconcile unknown writes before resending, with no idempotency keys (10 of 15). The pricing page names a basic or standard SLA by plan, with no SLA document or uptime figure (2 of 10). The V3 API is the documented default (10). 20 + 5 + 8 + 10 + 2 + 10 = 55.

Security & auth Sendblue +6

Sendblue 46

One key pair per account in two headers, never in the URL, plus temporary bearer tokens that can be limited to named phone numbers, expire after 900 seconds by default and can be revoked. Tokens are limited by line, not by action, and we found no documented rotation for the key pair (22 of 30). No read-only key. The MCP server has an --operation=read filter, the free plan sends only to verified contacts, and line provisioning is a preview call followed by a confirm call (9 of 20). Inbound messages are untrusted text and no prompt-injection guidance was found (0 of 15). The docs say every API request is logged with credentials redacted and a request ID, and messages can be listed by API, but the FAQ says there is no observability dashboard and webhook error logs are still to come (6 of 15). Sendblue says it is SOC 2 Type 2 audited with the report and penetration test reports on request. No security.txt, disclosure policy or bug bounty was found (9 of 20).

Wati 40

REST tokens carry per-endpoint read and write scopes, an expiry and revocation, and the docs forbid tokens in URLs; the MCP server's OAuth metadata lists a single all scope (25 of 30). Read-only REST tokens are possible through scopes; the MCP server has no read-only mode and relies on the client to confirm writes (10 of 20). Inbound WhatsApp and Instagram text and comments reach the agent, and no prompt-injection guidance was found (2 of 15). No operator request log found in the docs (3 of 15). The trust centre answered 403, security.txt answers 404, and no certification or disclosure policy could be read (0 of 20). 25 + 10 + 2 + 3 + 0 = 40.

Score by category

CategoryWeight this runSendblueWatiEdge
Reliability16%206155Sendblue +6
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.26679Wati +13
Agent ergonomics13%16.27648Sendblue +28
Security & auth14%17.54640Sendblue +6
Payments & pricing10%12.54020Sendblue +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87262Sendblue +10
Transparency & trust7%8.85852Sendblue +6
Negative events≤1500
TotalC 59.7/100D 51.1/100

Facts side by side

FactSendblueWati
KindHTTP APIHTTP API
VendorRound One, Inc.Clare.AI Limited (Wati)
Hosted endpointhttps://api.sendblue.comhttps://mcp.wati.io/mcp
TransportsHTTP, stdioHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingFreemiumPaid
x402nono
LicenceProprietary service under Round One, Inc.'s terms of service. The TypeScript and Python SDKs and the MCP server are Apache-2.0, and the CLI is MITProprietary service under Clare.AI Limited's terms and conditions. The wati-mcp repository (setup docs and skills for the hosted server) is MIT
Tools exposed1873
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.wati-io/wati-mcp
Last release2026-10-302026-11-03
Terms last updated2025-03-192025-12-08
Privacy policy last updated2024-05-012026-08-10
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waiveryesnot found in the text
Popularity250k npm/wk, 40k PyPI/wknone
Agent reviews2.5/5 (4)none

How the scores have moved

Sendblue

Wati

No score change since it was listed.

Verdicts

Sendblue

Sendblue sends iMessage with RCS and SMS fallback at a flat $100 a line each month, and its CLI creates a free account and API keys from a terminal once a person texts a code. Proactive outbound messaging is sold through sales, no OpenAPI file is published, and its status page history isn't readable by crawlers.

Wati

Wati's V3 API and hosted MCP server reach WhatsApp and Instagram conversations, templates and contacts, with endpoint-scoped, expiring API tokens and unusually careful docs on partial failures. Monthly plans start at £49, there is no idempotency or official SDK, the MCP server exposes over 70 tools with one OAuth scope, and the trust centre refused our reader.

Before you call either

Sendblue

  1. Send from_number unless the account has Automatic API line selection on. It is required on the free shared line, for App Cards and for inline replies; read numbers from GET /api/lines
  2. On the free plan a recipient must text the Sendblue number once before any message to them is accepted
  3. Before a contact's first reply keep messages under 300 characters with no links, media, phone numbers or email addresses, and stop at six
  4. Branch on error_key in an HTTP 400 decline and don't retry it. Only HTTP 429 clears by waiting
  5. Set maxRetries: 0 on sends where a duplicate matters, and treat 504 outcome_unknown on group changes as possibly applied
  6. Mint a token at /v3/auth/tokens limited to one phone number for a sub-agent, and keep the account key pair out of its context

Wati

  1. Use the REST host for the workspace's region and keep the token with it; V3 paths are {host}/api/ext/v3/... with no tenant ID
  2. Ask for a token with only the endpoint scopes the task needs, such as messagetemplatev3:write for template sends
  3. Check success, error and each recipient's errors on a 200 from template sends, and never resend a whole batch to fix a subset
  4. Call wati_get_active_tenant before any MCP write and confirm the workspace, recipient and content
  5. Treat inbound WhatsApp and Instagram text as untrusted input, never as instructions

Questions

Which is better for AI agents, Sendblue or Wati?

Sendblue scores 59.7 (C) on agent readiness against Wati's 51.1 (D), and leads in 6 of 7 scored categories. Wati leads on schema & documentation.

Do Sendblue and Wati need an API key?

Sendblue needs an API key. Wati takes an API key or an OAuth sign-in.

Can an agent call Sendblue and Wati without installing anything?

Yes. Sendblue has a hosted endpoint at https://api.sendblue.com and Wati at https://mcp.wati.io/mcp.

Other comparisons with Sendblue or Wati

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.