{
  "fixes": {
    "slug": "sendgrid",
    "name": "Twilio SendGrid",
    "listing": "https://www.anchorterminal.com/tools/sendgrid",
    "markdown": "# Fix list: Twilio SendGrid\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/sendgrid, the October 2026 research run, assessed 1 October 2026. Grade B, 63.6 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 Twilio SendGrid: 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. Payments \u0026 pricing, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0). Plan prices are public, but overage rates per 1,000 aren't (10). A 60-day trial at 100 emails a day with no card (20). Browser signup and sender verification, no autonomous route (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## 2. Reliability, 66 out of 100, up to 6.8 more on the total\n\nWhy it scored 66: SendGrid components (Mail Sending, API v3, SMTP, Parse API, Event Webhooks and more) sit on status.twilio.com (20). We couldn't read 90 days of SendGrid history. The history page loads its incidents with JavaScript, robots.txt blocks our reader from the incidents API, and on 2 October the RSS feed's 24 items were all scheduled maintenance from 1 October to 19 November. The front page showed no SendGrid incidents in its recent window on 1 October, so 10 rather than the 5 for no readable history (10). Per-endpoint limits come back in X-RateLimit headers, but the docs give no numbers (8). 429 with X-RateLimit-Reset, and no backoff or idempotency guidance (8). The Twilio APIs SLA, updated 9 April 2026, names the SendGrid Mail Send API among its Services APIs at 99.95 per cent, or 99.99 per cent with Enterprise Edition or a premium email package, with a 10 per cent service credit (10). GA (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## 3. Agent ergonomics, 60 out of 100, up to 6.5 more on the total\n\nWhy it scored 60: No official MCP that sends. POST /v3/mail/send returns 202 with no body, and Email Activity takes a query and a limit (12). limit and offset on suppressions and other lists (15). Error bodies name the field and link to help (15). No idempotency key on mail/send, so a retried send can go out twice. `mail_settings.sandbox_mode` validates without delivering (6). SDKs in seven languages, but personalizations make the simplest send a nested object (12).\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## 4. Schema \u0026 documentation, 72 out of 100, up to 4.6 more on the total\n\nWhy it scored 72: OpenAPI 3.1 specs for the whole v3 API in 46 JSON files at twilio/sendgrid-oai, last regenerated 24 March 2026 and still tagged 1.0.0-rc.13 (25). The listed llms.txt is Twilio's docs-wide file, and our reader found no SendGrid pages in it (3). The reference describes each endpoint but not when to avoid one (10). Typed from OpenAPI (12). Examples in the reference, and the spec documents an ErrorResponse with field and help on mail/send (12). v3 API and a CHANGELOG in the spec repository. We couldn't filter Twilio's changelog to SendGrid (10).\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## 5. Maintenance \u0026 community, 47 out of 100, up to 4.6 more on the total\n\nWhy it scored 47: Scored on the service, as the rubric asks for closed services. Twilio's changelog carries \"Update to Twilio SendGrid Link Branding: Automatic SSL Certificate Provisioning\" on 27 August 2026, 36 days before this check (20). We read the changelog back to 4 August and found that entry plus \"Dedicated IPs and IP Management for Twilio Email\" on 6 August. That's two in the 58 days we read, and we didn't read 3 July to 4 August, so we departed from the checklist and gave half (10 of 20). A public changelog with SendGrid entries, and support by ticket on paid plans. We couldn't see issue replies (8 of 15). Official SDKs exist in seven languages, but Node and Python last shipped on 19 September 2025, Go on 29 May 2025, and the OpenAPI specs last changed on 24 March 2026 (5 of 15). CI workflows exist in the Node SDK repository (4).\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## 6. Security \u0026 auth, 81 out of 100, up to 3.3 more on the total\n\nWhy it scored 81: Bearer keys with full, restricted or billing access, restricted keys carry per-endpoint scopes, subusers get their own keys, and IP access management limits where keys work (30). A key can hold only `mail.send`, and read-only scopes exist (18). The API doesn't return third-party content. Inbound Parse posts to your own URL (10). Email Activity keeps 3 or 7 days of message events by plan. We found no audit log of key use (8). Twilio holds SOC 2 Type II and ISO 27001, 27017 and 27018, though it says not every credential covers every product, and runs a HackerOne bug bounty and a disclosure programme. twilio.com has no security.txt (15).\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## 7. Transparency \u0026 trust, 79 out of 100, up to 1.8 more on the total\n\nMade of editorial 68, provenance 90.\n\nWhy it scored 79: Closed service under Twilio's terms, with MIT SDKs (20). The privacy notice (9 April 2026) and the DPA (9 April 2026) agree. Customer content is deleted 30 days after termination and from backups after 60 days, or one year for SendGrid backups, Email Activity keeps 3 or 7 days of events by plan, and SendGrid tracks opens and clicks with web beacons, which the notice discloses. Account data is kept \"as long as needed\" with no number (25 of 30). We found no dated SendGrid deprecation notices (5). Twilio's subprocessor page, updated September 2026, lists AWS for email routing in the USA and EU and AWS and Snowflake for Marketing Campaigns in the USA, and the DPA promises 10 days' notice of a new subprocessor and 30 for an infrastructure provider (18).\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- security.txt: could not be fetched (0 of 10)\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: SendGrid incident history for the last 90 days. The history page loads incidents with JavaScript, the incidents API is blocked to our reader by robots.txt, and the RSS feed now holds only upcoming maintenance.\n- unchecked: Twilio's changelog from 3 July to 4 August 2026. Two email entries turned up between 4 August and 30 September.\n- Twilio's changelog of 6 August 2026 announces dedicated IPs for \"Twilio Email\". We didn't establish whether that's SendGrid under a new name or a separate product that could supersede it.\n- Whether the llms.txt the listing names covers SendGrid at all. Our reader found no SendGrid pages in it on 1 October.\n- Overage rates per 1,000 and numeric rate limits, which we didn't find published.\n\n## Weaknesses\n\n- No official MCP server that can send, only Twilio's docs search\n- Node and Python SDKs last released on 19 September 2025, Go on 29 May 2025\n- Free plan is a 60-day trial, not a standing free tier\n- Overage rates and numeric rate limits aren't published\n- No idempotency key on mail/send\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- Give an agent that only sends a restricted key with just `mail.send`\n- Set `mail_settings.sandbox_mode` to validate payloads without delivery\n- Authenticate a domain or verify a single sender before the first send\n- Read X-RateLimit-Remaining and X-RateLimit-Reset and wait for the reset on 429\n- Don't blindly retry a timed-out mail/send. There's no idempotency key, so the message can go out twice\n\n## What the review panel asked for\n\n- Keep a free tier\n- Publish numeric limits\n- Document safe retries\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": "B",
    "score": 63.6,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0). Plan prices are public, but overage rates per 1,000 aren't (10). A 60-day trial at 100 emails a day with no card (20). Browser signup and sender verification, no autonomous route (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": "reliability",
        "name": "Reliability",
        "score": 66,
        "maxGain": 6.8,
        "reason": "SendGrid components (Mail Sending, API v3, SMTP, Parse API, Event Webhooks and more) sit on status.twilio.com (20). We couldn't read 90 days of SendGrid history. The history page loads its incidents with JavaScript, robots.txt blocks our reader from the incidents API, and on 2 October the RSS feed's 24 items were all scheduled maintenance from 1 October to 19 November. The front page showed no SendGrid incidents in its recent window on 1 October, so 10 rather than the 5 for no readable history (10). Per-endpoint limits come back in X-RateLimit headers, but the docs give no numbers (8). 429 with X-RateLimit-Reset, and no backoff or idempotency guidance (8). The Twilio APIs SLA, updated 9 April 2026, names the SendGrid Mail Send API among its Services APIs at 99.95 per cent, or 99.99 per cent with Enterprise Edition or a premium email package, with a 10 per cent service credit (10). GA (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"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 60,
        "maxGain": 6.5,
        "reason": "No official MCP that sends. POST /v3/mail/send returns 202 with no body, and Email Activity takes a query and a limit (12). limit and offset on suppressions and other lists (15). Error bodies name the field and link to help (15). No idempotency key on mail/send, so a retried send can go out twice. `mail_settings.sandbox_mode` validates without delivering (6). SDKs in seven languages, but personalizations make the simplest send a nested object (12).",
        "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": 72,
        "maxGain": 4.6,
        "reason": "OpenAPI 3.1 specs for the whole v3 API in 46 JSON files at twilio/sendgrid-oai, last regenerated 24 March 2026 and still tagged 1.0.0-rc.13 (25). The listed llms.txt is Twilio's docs-wide file, and our reader found no SendGrid pages in it (3). The reference describes each endpoint but not when to avoid one (10). Typed from OpenAPI (12). Examples in the reference, and the spec documents an ErrorResponse with field and help on mail/send (12). v3 API and a CHANGELOG in the spec repository. We couldn't filter Twilio's changelog to SendGrid (10).",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 47,
        "maxGain": 4.6,
        "reason": "Scored on the service, as the rubric asks for closed services. Twilio's changelog carries \"Update to Twilio SendGrid Link Branding: Automatic SSL Certificate Provisioning\" on 27 August 2026, 36 days before this check (20). We read the changelog back to 4 August and found that entry plus \"Dedicated IPs and IP Management for Twilio Email\" on 6 August. That's two in the 58 days we read, and we didn't read 3 July to 4 August, so we departed from the checklist and gave half (10 of 20). A public changelog with SendGrid entries, and support by ticket on paid plans. We couldn't see issue replies (8 of 15). Official SDKs exist in seven languages, but Node and Python last shipped on 19 September 2025, Go on 29 May 2025, and the OpenAPI specs last changed on 24 March 2026 (5 of 15). CI workflows exist in the Node SDK repository (4).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 81,
        "maxGain": 3.3,
        "reason": "Bearer keys with full, restricted or billing access, restricted keys carry per-endpoint scopes, subusers get their own keys, and IP access management limits where keys work (30). A key can hold only `mail.send`, and read-only scopes exist (18). The API doesn't return third-party content. Inbound Parse posts to your own URL (10). Email Activity keeps 3 or 7 days of message events by plan. We found no audit log of key use (8). Twilio holds SOC 2 Type II and ISO 27001, 27017 and 27018, though it says not every credential covers every product, and runs a HackerOne bug bounty and a disclosure programme. twilio.com has no security.txt (15).",
        "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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 79,
        "maxGain": 1.8,
        "reason": "Closed service under Twilio's terms, with MIT SDKs (20). The privacy notice (9 April 2026) and the DPA (9 April 2026) agree. Customer content is deleted 30 days after termination and from backups after 60 days, or one year for SendGrid backups, Email Activity keeps 3 or 7 days of events by plan, and SendGrid tracks opens and clicks with web beacons, which the notice discloses. Account data is kept \"as long as needed\" with no number (25 of 30). We found no dated SendGrid deprecation notices (5). Twilio's subprocessor page, updated September 2026, lists AWS for email routing in the USA and EU and AWS and Snowflake for Marketing Campaigns in the USA, and the DPA promises 10 days' notice of a new subprocessor and 30 for an infrastructure provider (18).",
        "blend": "editorial 68, provenance 90",
        "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"
      }
    ],
    "provenance": [
      {
        "label": "security.txt",
        "value": "could not be fetched",
        "points": 0,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: SendGrid incident history for the last 90 days. The history page loads incidents with JavaScript, the incidents API is blocked to our reader by robots.txt, and the RSS feed now holds only upcoming maintenance.",
      "unchecked: Twilio's changelog from 3 July to 4 August 2026. Two email entries turned up between 4 August and 30 September.",
      "Twilio's changelog of 6 August 2026 announces dedicated IPs for \"Twilio Email\". We didn't establish whether that's SendGrid under a new name or a separate product that could supersede it.",
      "Whether the llms.txt the listing names covers SendGrid at all. Our reader found no SendGrid pages in it on 1 October.",
      "Overage rates per 1,000 and numeric rate limits, which we didn't find published."
    ],
    "weaknesses": [
      "No official MCP server that can send, only Twilio's docs search",
      "Node and Python SDKs last released on 19 September 2025, Go on 29 May 2025",
      "Free plan is a 60-day trial, not a standing free tier",
      "Overage rates and numeric rate limits aren't published",
      "No idempotency key on mail/send"
    ],
    "agentNotes": [
      "Give an agent that only sends a restricted key with just `mail.send`",
      "Set `mail_settings.sandbox_mode` to validate payloads without delivery",
      "Authenticate a domain or verify a single sender before the first send",
      "Read X-RateLimit-Remaining and X-RateLimit-Reset and wait for the reset on 429",
      "Don't blindly retry a timed-out mail/send. There's no idempotency key, so the message can go out twice"
    ],
    "requests": [
      {
        "text": "Keep a free tier",
        "reviews": 1
      },
      {
        "text": "Publish numeric limits",
        "reviews": 1
      },
      {
        "text": "Document safe retries",
        "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"
  }
}