{
  "fixes": {
    "slug": "360dialog",
    "name": "360dialog WhatsApp API + MCP",
    "listing": "https://www.anchorterminal.com/tools/360dialog",
    "markdown": "# Fix list: 360dialog WhatsApp API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/360dialog, the October 2026 research run, assessed 1 October 2026. Grade D, 52.2 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 360dialog WhatsApp 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, 35 out of 100, up to 11.4 more on the total\n\nWhy it scored 35: The Messaging API takes one key per phone number in the D360-API-KEY header. Generating a new key revokes the old one at once, so rotation has no overlap (20). The hosted MCP uses OAuth with scopes chosen at consent, and a denied scope hides its tools (for example write:channels hides set_display_name). The messaging key has no read-only variant (10 of 20). Inbound WhatsApp messages are untrusted text. Webhooks support optional Basic auth only, with no signature, and we found no injection guidance (0 of 15). No customer audit log found. The docs say the Cloud API keeps messages for at most 30 days (5 of 15). The ISO 27001 reference in the docs is Meta's, for the Cloud API. No security.txt (per the 30 September check), bug bounty or 360dialog certification found, and the Legal Information page lists none (0 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. Payments \u0026 pricing, 35 out of 100, up to 8.1 more on the total\n\nWhy it scored 35: No x402, MPP or L402 (0). Channel plans are public at €49, €99 or €249 a number a month, and Meta's per-message fees pass through at cost on Meta's rate card, plus 7 per cent on marketing sent through /messages (15 of 20). A sandbox key arrives by WhatsApp after sending START to a number, with 200 test messages to one recipient and no card (20). Production needs a Hub signup and Meta business verification, and even the sandbox needs a person's WhatsApp (0).\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## 3. Maintenance \u0026 community, 8 out of 100, up to 8.1 more on the total\n\nWhy it scored 8: No changelog or release notes found, so we couldn't date the last API change (0). No dated entries in the last 90 days (0). Closed service with a support response-time page and no public changelog (8 of 15). No official SDKs (0). No packages to assess (0).\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## 4. Agent ergonomics, 53 out of 100, up to 7.6 more on the total\n\nWhy it scored 53: Responses follow Meta's Cloud API shapes. GET /message_templates takes a `fields` list for field selection and a `limit` (18 of 25). Cursor pagination with `after` and `before` and next and previous links on the template list. We checked that list only (15 of 20). Error codes with resolution steps an agent can act on (15 of 20). No idempotency key found, and the MCP docs don't mention tool annotations (0 of 20). No official SDKs. A send needs only the D360-API-KEY header and a Cloud API message body (5 of 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## 5. Schema \u0026 documentation, 70 out of 100, up to 4.9 more on the total\n\nWhy it scored 70: The Markdown reference pages embed an OpenAPI 3.1.0 document titled Messaging API, version 1.50.7, with a D360-API-KEY header scheme and response schemas. We read the Templates section in full. We found no standalone download, so an agent has to collect it page by page (20 of 25). llms.txt listing 297 pages, a .md version of every page and an ?ask= query parameter that answers questions (10). API reference pages describe endpoints and parameters, mostly following Meta's Cloud API payloads (12 of 20). Typed query parameters and response schemas in the spec, with enums not checked (10 of 15). More than 60 error codes, each with a suggested fix (13 of 15). The spec carries a version number and flags the legacy /v1/configs template endpoints as deprecated, but we found no changelog (5 of 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## 6. Transparency \u0026 trust, 50 out of 100, up to 4.4 more on the total\n\nMade of editorial 35, provenance 65.\n\nWhy it scored 50: Closed service with terms of use in the Hub (15). The privacy policy covers the website, names 360dialog GmbH in Grünwald and was updated on 10 September 2026. The Legal Information page links two English DPA files we didn't open, and the docs say the Cloud API keeps messages for at most 30 days, but we found no sub-processor list for the service (15 of 30). No deprecation policy. The OpenAPI flags deprecated template endpoints without dates (5 of 20). Website trackers are listed with locations, but service sub-processors and hosting locations aren't (0 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- Endpoint on the vendor's domain: waba-v2.360dialog.io is not on 360dialog.com (0 of 15)\n- Changelog: not found (0 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Reliability, 83 out of 100, up to 3.4 more on the total\n\nWhy it scored 83: Status page at status.360dialog.com on Instatus, with 10 360dialog components, 3 Meta ones and subscriptions (20). No notices from July to 2 October 2026. The page does log incidents, including Meta's (a 4 hour 25 minute Meta messaging outage on 12 June, an 18 minute disruption to waba-v2.360dialog.io on 14 May), so the quiet 90 days read as clean (30). Throughput is published, up to 80 messages a second on standard plans and 1,000 on the Higher Throughput tier (15). The error list maps the rate-limit error to throttling or exponential back-off, with no Retry-After and no idempotency key for sends (8 of 15). No SLA. The support page sets first-response targets (under 24 hours Basic, 4 hours Regular, 30 minutes Premium) and aims to resolve cases within 48 hours without guaranteeing it, and nothing commits to uptime (0). The Messaging 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## 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- unchecked: whether 360dialog holds its own ISO 27001 or SOC 2 certification. The Legal Information and architecture pages name none\n- The MCP's tool count and whether its tools carry annotations. The MCP page names 4 tools and no full list\n- Whether the embedded OpenAPI covers messages, media and webhooks as well as templates, and whether a standalone file exists. The listing's `openapi` stays null until one does\n- What the two DPA files say about sub-processors and hosting locations\n\n## Weaknesses\n\n- No changelog, official SDK or standalone OpenAPI download\n- One key per number with no scopes, and a new key revokes the old one at once\n- Webhooks support Basic auth only, with no signature\n- No uptime SLA on any plan, only support response targets\n- The hosted MCP can't send messages and doesn't publish its tool list\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- Send marketing templates through the Marketing Messages API, /messages adds 7 per cent\n- Ask a docs page a question with `?ask=` before reading the whole page\n- Pass `fields` and `limit` on GET /message_templates and page with the `after` cursor\n- Coordinate key rotation, a new key cuts off every client using the old one\n- Answer each webhook with 200 within 5 seconds and process it asynchronously\n\n## What the review panel asked for\n\n- Show Meta's rates alongside\n- State failed-message billing\n- Publish an SLA\n- An idempotency key for sends\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": "D",
    "score": 52.2,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 35,
        "maxGain": 11.4,
        "reason": "The Messaging API takes one key per phone number in the D360-API-KEY header. Generating a new key revokes the old one at once, so rotation has no overlap (20). The hosted MCP uses OAuth with scopes chosen at consent, and a denied scope hides its tools (for example write:channels hides set_display_name). The messaging key has no read-only variant (10 of 20). Inbound WhatsApp messages are untrusted text. Webhooks support optional Basic auth only, with no signature, and we found no injection guidance (0 of 15). No customer audit log found. The docs say the Cloud API keeps messages for at most 30 days (5 of 15). The ISO 27001 reference in the docs is Meta's, for the Cloud API. No security.txt (per the 30 September check), bug bounty or 360dialog certification found, and the Legal Information page lists none (0 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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 35,
        "maxGain": 8.1,
        "reason": "No x402, MPP or L402 (0). Channel plans are public at €49, €99 or €249 a number a month, and Meta's per-message fees pass through at cost on Meta's rate card, plus 7 per cent on marketing sent through /messages (15 of 20). A sandbox key arrives by WhatsApp after sending START to a number, with 200 test messages to one recipient and no card (20). Production needs a Hub signup and Meta business verification, and even the sandbox needs a person's WhatsApp (0).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 8,
        "maxGain": 8.1,
        "reason": "No changelog or release notes found, so we couldn't date the last API change (0). No dated entries in the last 90 days (0). Closed service with a support response-time page and no public changelog (8 of 15). No official SDKs (0). No packages to assess (0).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 53,
        "maxGain": 7.6,
        "reason": "Responses follow Meta's Cloud API shapes. GET /message_templates takes a `fields` list for field selection and a `limit` (18 of 25). Cursor pagination with `after` and `before` and next and previous links on the template list. We checked that list only (15 of 20). Error codes with resolution steps an agent can act on (15 of 20). No idempotency key found, and the MCP docs don't mention tool annotations (0 of 20). No official SDKs. A send needs only the D360-API-KEY header and a Cloud API message body (5 of 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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 70,
        "maxGain": 4.9,
        "reason": "The Markdown reference pages embed an OpenAPI 3.1.0 document titled Messaging API, version 1.50.7, with a D360-API-KEY header scheme and response schemas. We read the Templates section in full. We found no standalone download, so an agent has to collect it page by page (20 of 25). llms.txt listing 297 pages, a .md version of every page and an ?ask= query parameter that answers questions (10). API reference pages describe endpoints and parameters, mostly following Meta's Cloud API payloads (12 of 20). Typed query parameters and response schemas in the spec, with enums not checked (10 of 15). More than 60 error codes, each with a suggested fix (13 of 15). The spec carries a version number and flags the legacy /v1/configs template endpoints as deprecated, but we found no changelog (5 of 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"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 50,
        "maxGain": 4.4,
        "reason": "Closed service with terms of use in the Hub (15). The privacy policy covers the website, names 360dialog GmbH in Grünwald and was updated on 10 September 2026. The Legal Information page links two English DPA files we didn't open, and the docs say the Cloud API keeps messages for at most 30 days, but we found no sub-processor list for the service (15 of 30). No deprecation policy. The OpenAPI flags deprecated template endpoints without dates (5 of 20). Website trackers are listed with locations, but service sub-processors and hosting locations aren't (0 of 20).",
        "blend": "editorial 35, provenance 65",
        "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": "reliability",
        "name": "Reliability",
        "score": 83,
        "maxGain": 3.4,
        "reason": "Status page at status.360dialog.com on Instatus, with 10 360dialog components, 3 Meta ones and subscriptions (20). No notices from July to 2 October 2026. The page does log incidents, including Meta's (a 4 hour 25 minute Meta messaging outage on 12 June, an 18 minute disruption to waba-v2.360dialog.io on 14 May), so the quiet 90 days read as clean (30). Throughput is published, up to 80 messages a second on standard plans and 1,000 on the Higher Throughput tier (15). The error list maps the rate-limit error to throttling or exponential back-off, with no Retry-After and no idempotency key for sends (8 of 15). No SLA. The support page sets first-response targets (under 24 hours Basic, 4 hours Regular, 30 minutes Premium) and aims to resolve cases within 48 hours without guaranteeing it, and nothing commits to uptime (0). The Messaging 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"
      }
    ],
    "provenance": [
      {
        "label": "Endpoint on the vendor's domain",
        "value": "waba-v2.360dialog.io is not on 360dialog.com",
        "points": 0,
        "max": 15
      },
      {
        "label": "Changelog",
        "value": "not found",
        "points": 0,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: whether 360dialog holds its own ISO 27001 or SOC 2 certification. The Legal Information and architecture pages name none",
      "The MCP's tool count and whether its tools carry annotations. The MCP page names 4 tools and no full list",
      "Whether the embedded OpenAPI covers messages, media and webhooks as well as templates, and whether a standalone file exists. The listing's `openapi` stays null until one does",
      "What the two DPA files say about sub-processors and hosting locations"
    ],
    "weaknesses": [
      "No changelog, official SDK or standalone OpenAPI download",
      "One key per number with no scopes, and a new key revokes the old one at once",
      "Webhooks support Basic auth only, with no signature",
      "No uptime SLA on any plan, only support response targets",
      "The hosted MCP can't send messages and doesn't publish its tool list"
    ],
    "agentNotes": [
      "Send marketing templates through the Marketing Messages API, /messages adds 7 per cent",
      "Ask a docs page a question with `?ask=` before reading the whole page",
      "Pass `fields` and `limit` on GET /message_templates and page with the `after` cursor",
      "Coordinate key rotation, a new key cuts off every client using the old one",
      "Answer each webhook with 200 within 5 seconds and process it asynchronously"
    ],
    "requests": [
      {
        "text": "Show Meta's rates alongside",
        "reviews": 1
      },
      {
        "text": "State failed-message billing",
        "reviews": 1
      },
      {
        "text": "Publish an SLA",
        "reviews": 1
      },
      {
        "text": "An idempotency key for sends",
        "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"
  }
}