{
  "fixes": {
    "slug": "amazon-ses",
    "name": "Amazon SES",
    "listing": "https://www.anchorterminal.com/tools/amazon-ses",
    "markdown": "# Fix list: Amazon SES\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-ses, the October 2026 research run, assessed 1 October 2026. Grade BB, 75.1 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 Amazon SES: 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, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: No x402, MPP or L402 (0). Per-1,000 prices for a la carte and the three plans published without login (20). No SES free allowance. New AWS customers get up to $200 in Free Tier credits, but AWS signup takes a payment card (0). A person signs up and has to request production access, so 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. Agent ergonomics, 64 out of 100, up to 5.9 more on the total\n\nWhy it scored 64: No SES-specific MCP. The AWS MCP Server with an amazon-ses skill covers sending setup only. API responses are compact and list actions take PageSize and NextToken (15). Paginated lists and filters on suppression and contact lists (15). SendEmail declares eight typed errors, among them MessageRejected, MailFromDomainNotVerifiedException, SendingPausedException and TooManyRequestsException (16). No idempotency token on SendEmail, so a retried send can go out twice. SDK retries cover throttling (8). SDKs in every major language, but every call needs SigV4 and a send needs a nested Content structure (10).\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## 3. Schema \u0026 documentation, 85 out of 100, up to 2.4 more on the total\n\nWhy it scored 85: No OpenAPI, but the SES v2 Smithy model is published in aws/api-models-aws with types, required members and enums (25). llms.txt for the developer guide with Markdown pages (10). The API reference explains each action, rarely when not to use one (12). Typed inputs from the model, with enums and length limits (14). Each action lists its errors, and the guide has examples (12). Versioned API (2019-09-27). The document history page wouldn't load for us, so we lean on the model's dated changes (12).\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## 4. Security \u0026 auth, 87 out of 100, up to 2.3 more on the total\n\nWhy it scored 87: IAM with policies per action and identity, condition keys such as ses:FromAddress, temporary credentials and rotation (30). Policies can allow only SendEmail from one identity, and AWS has a read-only managed policy. No confirmation step, which IAM leaves to the caller (16). The API doesn't return third-party content. Inbound mail goes to S3, SNS or Lambda rather than through SES calls (10). CloudTrail records SES API calls and configuration sets publish per-message events (15). SES is in scope for SOC 1, 2 and 3 (page updated 11 August 2026), AWS runs a vulnerability disclosure programme on HackerOne and publishes security bulletins, but aws.amazon.com's security.txt expired on 24 September 2026 and we found no paid bug bounty (16).\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## 5. Transparency \u0026 trust, 77 out of 100, up to 2 more on the total\n\nMade of editorial 59, provenance 95.\n\nWhy it scored 77: Closed service under the AWS Customer Agreement, with Apache-2.0 SDKs (20). The AWS privacy notice and customer agreement cover SES per the provenance check. We found no SES-specific retention statement this run (12). The move of new accounts to the Essentials plan carries a dated notice (21 July 2026) on the pricing page, and AWS dates API changes in the SDK changelogs (15). Data stays in the Region the customer picks, and quotas and sandbox status are per Region. We didn't read AWS's subprocessor list this run (12).\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: published but past its Expires date (5 of 10)\n\n## 6. Maintenance \u0026 community, 85 out of 100, up to 1.3 more on the total\n\nWhy it scored 85: The SES v2 model changed on 29 September and the JavaScript SDK shipped v3.1145.0 on 1 October (30). SES v2 model changes on 20 and 22 July, 20 August, and 1, 17 and 29 September (20). Closed service with dated SDK changelogs and AWS re:Post. Direct support is a paid plan (10). Official SDKs released daily (15). The JavaScript SDK repository releases from CI every working day (10).\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## 7. Reliability, 95 out of 100, up to 1 more on the total\n\nWhy it scored 95: AWS Health Dashboard with per-service, per-Region history and RSS feeds (20). The SES us-east-1 feed carries no events. We checked only that Region (30). Sandbox quotas (200 messages in 24 hours, 1 a second), per-account send rate and daily quota after production access, and 1 request a second for API actions other than sending (15). ThrottlingException with 'Maximum sending rate exceeded' or 'Daily message quota exceeded' and advice to wait up to 10 minutes and retry. SES drops over-quota messages rather than queueing them, and SendEmail has no idempotency token (10). SES is covered by the Amazon User Engagement SLA with Pinpoint and End User Messaging (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## 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- Incident history for Regions other than us-east-1\n- unchecked: SES-specific data retention statement and AWS subprocessor list\n- The SES document history page, which returned a redirect loop to our reader\n\n## Weaknesses\n\n- Sandbox limits new accounts to verified recipients and 200 messages a day until production access is granted\n- SigV4 signing makes a plain curl or quick agent call awkward\n- No SES-specific MCP server, and the AWS skill covers sending setup only\n- No idempotency token on SendEmail, and over-quota messages are dropped\n- security.txt on aws.amazon.com expired on 24 September 2026\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- Call GetAccount and check ProductionAccessEnabled and the send quota before emailing arbitrary recipients\n- Verify the From domain as an identity first. Sends from unverified identities fail even in production\n- Use the mailbox simulator (success@simulator.amazonses.com) to test bounces and complaints without hurting reputation\n- Use the same Region the identity was verified in, since quotas and sandbox status are per Region\n- On a throttling error, wait and retry the send. SES drops messages over quota rather than queueing them\n\n## What the review panel asked for\n\n- Idempotency on SendEmail\n- SES MCP with receiving\n- a readable document history\n- idempotency token on sends\n- an SES MCP server\n- OpenAPI beside Smithy\n- an SES MCP that covers receiving\n- SES retention statement\n- Accept x402 for sending\n- Add an idempotency token\n- Queue over-quota 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": "BB",
    "score": 75.1,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "No x402, MPP or L402 (0). Per-1,000 prices for a la carte and the three plans published without login (20). No SES free allowance. New AWS customers get up to $200 in Free Tier credits, but AWS signup takes a payment card (0). A person signs up and has to request production access, so 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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 64,
        "maxGain": 5.9,
        "reason": "No SES-specific MCP. The AWS MCP Server with an amazon-ses skill covers sending setup only. API responses are compact and list actions take PageSize and NextToken (15). Paginated lists and filters on suppression and contact lists (15). SendEmail declares eight typed errors, among them MessageRejected, MailFromDomainNotVerifiedException, SendingPausedException and TooManyRequestsException (16). No idempotency token on SendEmail, so a retried send can go out twice. SDK retries cover throttling (8). SDKs in every major language, but every call needs SigV4 and a send needs a nested Content structure (10).",
        "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": 85,
        "maxGain": 2.4,
        "reason": "No OpenAPI, but the SES v2 Smithy model is published in aws/api-models-aws with types, required members and enums (25). llms.txt for the developer guide with Markdown pages (10). The API reference explains each action, rarely when not to use one (12). Typed inputs from the model, with enums and length limits (14). Each action lists its errors, and the guide has examples (12). Versioned API (2019-09-27). The document history page wouldn't load for us, so we lean on the model's dated changes (12).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 87,
        "maxGain": 2.3,
        "reason": "IAM with policies per action and identity, condition keys such as ses:FromAddress, temporary credentials and rotation (30). Policies can allow only SendEmail from one identity, and AWS has a read-only managed policy. No confirmation step, which IAM leaves to the caller (16). The API doesn't return third-party content. Inbound mail goes to S3, SNS or Lambda rather than through SES calls (10). CloudTrail records SES API calls and configuration sets publish per-message events (15). SES is in scope for SOC 1, 2 and 3 (page updated 11 August 2026), AWS runs a vulnerability disclosure programme on HackerOne and publishes security bulletins, but aws.amazon.com's security.txt expired on 24 September 2026 and we found no paid bug bounty (16).",
        "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": 77,
        "maxGain": 2,
        "reason": "Closed service under the AWS Customer Agreement, with Apache-2.0 SDKs (20). The AWS privacy notice and customer agreement cover SES per the provenance check. We found no SES-specific retention statement this run (12). The move of new accounts to the Essentials plan carries a dated notice (21 July 2026) on the pricing page, and AWS dates API changes in the SDK changelogs (15). Data stays in the Region the customer picks, and quotas and sandbox status are per Region. We didn't read AWS's subprocessor list this run (12).",
        "blend": "editorial 59, provenance 95",
        "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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 85,
        "maxGain": 1.3,
        "reason": "The SES v2 model changed on 29 September and the JavaScript SDK shipped v3.1145.0 on 1 October (30). SES v2 model changes on 20 and 22 July, 20 August, and 1, 17 and 29 September (20). Closed service with dated SDK changelogs and AWS re:Post. Direct support is a paid plan (10). Official SDKs released daily (15). The JavaScript SDK repository releases from CI every working day (10).",
        "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": "reliability",
        "name": "Reliability",
        "score": 95,
        "maxGain": 1,
        "reason": "AWS Health Dashboard with per-service, per-Region history and RSS feeds (20). The SES us-east-1 feed carries no events. We checked only that Region (30). Sandbox quotas (200 messages in 24 hours, 1 a second), per-account send rate and daily quota after production access, and 1 request a second for API actions other than sending (15). ThrottlingException with 'Maximum sending rate exceeded' or 'Daily message quota exceeded' and advice to wait up to 10 minutes and retry. SES drops over-quota messages rather than queueing them, and SendEmail has no idempotency token (10). SES is covered by the Amazon User Engagement SLA with Pinpoint and End User Messaging (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"
      }
    ],
    "provenance": [
      {
        "label": "security.txt",
        "value": "published but past its Expires date",
        "points": 5,
        "max": 10
      }
    ],
    "unchecked": [
      "Incident history for Regions other than us-east-1",
      "unchecked: SES-specific data retention statement and AWS subprocessor list",
      "The SES document history page, which returned a redirect loop to our reader"
    ],
    "weaknesses": [
      "Sandbox limits new accounts to verified recipients and 200 messages a day until production access is granted",
      "SigV4 signing makes a plain curl or quick agent call awkward",
      "No SES-specific MCP server, and the AWS skill covers sending setup only",
      "No idempotency token on SendEmail, and over-quota messages are dropped",
      "security.txt on aws.amazon.com expired on 24 September 2026"
    ],
    "agentNotes": [
      "Call GetAccount and check ProductionAccessEnabled and the send quota before emailing arbitrary recipients",
      "Verify the From domain as an identity first. Sends from unverified identities fail even in production",
      "Use the mailbox simulator (success@simulator.amazonses.com) to test bounces and complaints without hurting reputation",
      "Use the same Region the identity was verified in, since quotas and sandbox status are per Region",
      "On a throttling error, wait and retry the send. SES drops messages over quota rather than queueing them"
    ],
    "requests": [
      {
        "text": "Idempotency on SendEmail",
        "reviews": 1
      },
      {
        "text": "SES MCP with receiving",
        "reviews": 1
      },
      {
        "text": "a readable document history",
        "reviews": 1
      },
      {
        "text": "idempotency token on sends",
        "reviews": 1
      },
      {
        "text": "an SES MCP server",
        "reviews": 1
      },
      {
        "text": "OpenAPI beside Smithy",
        "reviews": 1
      },
      {
        "text": "an SES MCP that covers receiving",
        "reviews": 1
      },
      {
        "text": "SES retention statement",
        "reviews": 1
      },
      {
        "text": "Accept x402 for sending",
        "reviews": 1
      },
      {
        "text": "Add an idempotency token",
        "reviews": 1
      },
      {
        "text": "Queue over-quota 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"
  }
}