{
  "fixes": {
    "slug": "amazon-s3",
    "name": "Amazon S3",
    "listing": "https://www.anchorterminal.com/tools/amazon-s3",
    "markdown": "# Fix list: Amazon S3\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/amazon-s3, the October 2026 research run, assessed 1 October 2026. Grade A, 79.3 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 S3: 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-GB and per-request prices are public without a login, though the Standard table on the pricing page renders by script and the figures come from AWS's public price feed (20). New accounts get up to $200 in Free Tier credits, but AWS signup asks for a payment card (0). A person signs up in a browser (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, 83 out of 100, up to 2.8 more on the total\n\nWhy it scored 83: No S3-specific MCP server, so this is graded as an API. ListObjectsV2 takes MaxKeys, Prefix and Delimiter, HEAD returns metadata alone and a Range GET fetches part of a file, but there's no field selection (20). Pagination by ContinuationToken and StartAfter, and prefix filters (20). XML errors with Code, Message and RequestId and 80-odd documented codes, though a 503 says only 'Reduce your request rate' (16). Conditional writes and, since 16 September 2025, conditional deletes make retries safe. No tool annotations, since there are no S3 tools (16). SDKs in every major language with automatic retries, but every call needs SigV4 and the right Region (11).\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. Security \u0026 auth, 86 out of 100, up to 2.5 more on the total\n\nWhy it scored 86: IAM policies per action, bucket and prefix, STS session credentials with session policies, and key rotation. Presigned URLs carry a signature, never the secret (30). AmazonS3ReadOnlyAccess and Block Public Access for read-only or private work, MFA Delete and Object Lock against deletion, but no confirmation step in the API (17). Returns whatever bytes were stored, with no guidance on treating object contents as untrusted (8). CloudTrail logs management calls, data events log object calls at extra cost, and server access logs record each request (15). A vulnerability disclosure programme and security bulletins, and AWS's SOC and ISO 27001 reports, which we didn't re-read for S3 this run. security.txt on aws.amazon.com expired on 24 September 2026, per the 30 September check (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## 4. Transparency \u0026 trust, 80 out of 100, up to 1.8 more on the total\n\nMade of editorial 65, provenance 95.\n\nWhy it scored 80: Closed service under the AWS Customer Agreement and Service Terms (updated 15 September 2026), with the SDKs and Smithy models under Apache-2.0 (18, three over the closed-service line for the open models). The privacy notice, the GDPR DPA in the Service Terms and deletion after account closure come from the 30 September check, and we didn't re-read them (20). Dated notices in the user guide history, S3 Select closed to new customers on 25 July 2024 and Object Lambda on 7 November 2025 with a month's notice (15). Data stays in the Region you pick. We didn't read AWS's sub-processor 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## 5. Maintenance \u0026 community, 83 out of 100, up to 1.5 more on the total\n\nWhy it scored 83: The S3 model in aws/api-models-aws last changed on 30 September 2026 (30). Model changes on 16 July, 6 August, 8 September (Object Lock event holds), 11 September and 30 September (20). Closed service with dated model changes, a What's New feed and AWS re:Post. Direct support is a paid plan (10). Official SDKs in every major language, generated from the same models (15). We didn't check SDK CI this run (8).\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. Schema \u0026 documentation, 92 out of 100, up to 1.3 more on the total\n\nWhy it scored 92: No OpenAPI, but the S3 Smithy model (s3-2006-03-01.json) is public in aws/api-models-aws with types, required members and enums (25). An llms.txt for the user guide with 500-odd links, and each page has a Markdown twin (10). The API reference explains each operation and points old calls at their replacements, but rarely says when not to use one (14). Typed inputs from the model, with enums and constraints (14). Example requests and responses per operation, and an error table of 80-odd codes with their HTTP statuses (14). API version 2006-03-01, model changes dated in git, a What's New feed and a user guide history (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## 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 S3 feeds for us-east-1 and us-west-2 carry no events. We read only those two Regions, and the dashboard's own history view renders by script (25). 3,500 writes and 5,500 reads a second per prefix, with no limit on prefixes (15). 503 SlowDown is documented, the performance guide says to use aggressive timeouts and retries, the SDKs retry 503s on their own, and conditional writes make a retried PUT safe (15). SLA of 99.9 per cent a month for Standard, with 10, 25 and 100 per cent credits (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- unchecked: S3 events in Regions other than us-east-1 and us-west-2, since the Health Dashboard history renders by script\n- unchecked: the per-GB internet egress rate after 100 GB a month, which the pricing page renders by script\n- Whether the hosted AWS MCP Server is GA and what it costs; its overview page didn't say\n- The listing said no official MCP server reaches objects; AWS's general MCP server runs AWS API calls, so the summary and details were patched\n\n## Weaknesses\n\n- Egress to the internet is billed per GB after 100 GB a month\n- The pricing page renders the Standard table by script, so an agent reading it sees no Standard rate\n- Signup needs a person in a browser and a payment card\n- No S3-specific MCP server; AWS's general MCP server reaches S3 through IAM credentials and generic API calls\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- Hold STS session credentials scoped by a session policy, never a long-lived IAM user key\n- Sign presigned URLs with credentials that outlive the URL; a URL signed with a one-hour session token dies with the token\n- Send If-None-Match with * on PutObject so a retry can't overwrite a file another call wrote\n- Page ListObjectsV2 with MaxKeys and ContinuationToken, and always pass a Prefix\n- On 503 SlowDown back off and spread keys over more prefixes, since each prefix gets 3,500 writes a second\n\n## What the review panel asked for\n\n- Add a programmatic signup\n- Machine payment route\n- Plain-HTML pricing table\n- Dedicated S3 MCP server\n- longer notice before closing a feature to new customers\n- Put the retry rule in the 503 error text\n- static pricing tables\n- readable incident history\n- Put retry advice beside the 503 code\n- Render prices as text\n- Publish egress rate\n- a renewed security.txt\n- untrusted-content guidance\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": "A",
    "score": 79.3,
    "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-GB and per-request prices are public without a login, though the Standard table on the pricing page renders by script and the figures come from AWS's public price feed (20). New accounts get up to $200 in Free Tier credits, but AWS signup asks for a payment card (0). A person signs up in a browser (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": 83,
        "maxGain": 2.8,
        "reason": "No S3-specific MCP server, so this is graded as an API. ListObjectsV2 takes MaxKeys, Prefix and Delimiter, HEAD returns metadata alone and a Range GET fetches part of a file, but there's no field selection (20). Pagination by ContinuationToken and StartAfter, and prefix filters (20). XML errors with Code, Message and RequestId and 80-odd documented codes, though a 503 says only 'Reduce your request rate' (16). Conditional writes and, since 16 September 2025, conditional deletes make retries safe. No tool annotations, since there are no S3 tools (16). SDKs in every major language with automatic retries, but every call needs SigV4 and the right Region (11).",
        "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": "security",
        "name": "Security \u0026 auth",
        "score": 86,
        "maxGain": 2.5,
        "reason": "IAM policies per action, bucket and prefix, STS session credentials with session policies, and key rotation. Presigned URLs carry a signature, never the secret (30). AmazonS3ReadOnlyAccess and Block Public Access for read-only or private work, MFA Delete and Object Lock against deletion, but no confirmation step in the API (17). Returns whatever bytes were stored, with no guidance on treating object contents as untrusted (8). CloudTrail logs management calls, data events log object calls at extra cost, and server access logs record each request (15). A vulnerability disclosure programme and security bulletins, and AWS's SOC and ISO 27001 reports, which we didn't re-read for S3 this run. security.txt on aws.amazon.com expired on 24 September 2026, per the 30 September check (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": 80,
        "maxGain": 1.8,
        "reason": "Closed service under the AWS Customer Agreement and Service Terms (updated 15 September 2026), with the SDKs and Smithy models under Apache-2.0 (18, three over the closed-service line for the open models). The privacy notice, the GDPR DPA in the Service Terms and deletion after account closure come from the 30 September check, and we didn't re-read them (20). Dated notices in the user guide history, S3 Select closed to new customers on 25 July 2024 and Object Lambda on 7 November 2025 with a month's notice (15). Data stays in the Region you pick. We didn't read AWS's sub-processor list this run (12).",
        "blend": "editorial 65, 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": 83,
        "maxGain": 1.5,
        "reason": "The S3 model in aws/api-models-aws last changed on 30 September 2026 (30). Model changes on 16 July, 6 August, 8 September (Object Lock event holds), 11 September and 30 September (20). Closed service with dated model changes, a What's New feed and AWS re:Post. Direct support is a paid plan (10). Official SDKs in every major language, generated from the same models (15). We didn't check SDK CI this run (8).",
        "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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 92,
        "maxGain": 1.3,
        "reason": "No OpenAPI, but the S3 Smithy model (s3-2006-03-01.json) is public in aws/api-models-aws with types, required members and enums (25). An llms.txt for the user guide with 500-odd links, and each page has a Markdown twin (10). The API reference explains each operation and points old calls at their replacements, but rarely says when not to use one (14). Typed inputs from the model, with enums and constraints (14). Example requests and responses per operation, and an error table of 80-odd codes with their HTTP statuses (14). API version 2006-03-01, model changes dated in git, a What's New feed and a user guide history (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": "reliability",
        "name": "Reliability",
        "score": 95,
        "maxGain": 1,
        "reason": "AWS Health Dashboard with per-service, per-Region history and RSS feeds (20). The S3 feeds for us-east-1 and us-west-2 carry no events. We read only those two Regions, and the dashboard's own history view renders by script (25). 3,500 writes and 5,500 reads a second per prefix, with no limit on prefixes (15). 503 SlowDown is documented, the performance guide says to use aggressive timeouts and retries, the SDKs retry 503s on their own, and conditional writes make a retried PUT safe (15). SLA of 99.9 per cent a month for Standard, with 10, 25 and 100 per cent credits (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": [
      "unchecked: S3 events in Regions other than us-east-1 and us-west-2, since the Health Dashboard history renders by script",
      "unchecked: the per-GB internet egress rate after 100 GB a month, which the pricing page renders by script",
      "Whether the hosted AWS MCP Server is GA and what it costs; its overview page didn't say",
      "The listing said no official MCP server reaches objects; AWS's general MCP server runs AWS API calls, so the summary and details were patched"
    ],
    "weaknesses": [
      "Egress to the internet is billed per GB after 100 GB a month",
      "The pricing page renders the Standard table by script, so an agent reading it sees no Standard rate",
      "Signup needs a person in a browser and a payment card",
      "No S3-specific MCP server; AWS's general MCP server reaches S3 through IAM credentials and generic API calls",
      "security.txt on aws.amazon.com expired on 24 September 2026"
    ],
    "agentNotes": [
      "Hold STS session credentials scoped by a session policy, never a long-lived IAM user key",
      "Sign presigned URLs with credentials that outlive the URL; a URL signed with a one-hour session token dies with the token",
      "Send If-None-Match with * on PutObject so a retry can't overwrite a file another call wrote",
      "Page ListObjectsV2 with MaxKeys and ContinuationToken, and always pass a Prefix",
      "On 503 SlowDown back off and spread keys over more prefixes, since each prefix gets 3,500 writes a second"
    ],
    "requests": [
      {
        "text": "Add a programmatic signup",
        "reviews": 1
      },
      {
        "text": "Machine payment route",
        "reviews": 1
      },
      {
        "text": "Plain-HTML pricing table",
        "reviews": 1
      },
      {
        "text": "Dedicated S3 MCP server",
        "reviews": 1
      },
      {
        "text": "longer notice before closing a feature to new customers",
        "reviews": 1
      },
      {
        "text": "Put the retry rule in the 503 error text",
        "reviews": 1
      },
      {
        "text": "static pricing tables",
        "reviews": 1
      },
      {
        "text": "readable incident history",
        "reviews": 1
      },
      {
        "text": "Put retry advice beside the 503 code",
        "reviews": 1
      },
      {
        "text": "Render prices as text",
        "reviews": 1
      },
      {
        "text": "Publish egress rate",
        "reviews": 1
      },
      {
        "text": "a renewed security.txt",
        "reviews": 1
      },
      {
        "text": "untrusted-content guidance",
        "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"
  }
}