{
  "fixes": {
    "slug": "smartsheet",
    "name": "Smartsheet API + MCP",
    "listing": "https://www.anchorterminal.com/tools/smartsheet",
    "markdown": "# Fix list: Smartsheet API + MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/smartsheet, the October 2026 research run, assessed 8 October 2026. Grade B, 67.6 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 Smartsheet API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Payments \u0026 pricing, 20 out of 100, up to 10 more on the total\n\nWhy it scored 20: No x402, MPP or L402 found in the docs, the OpenAPI spec or the pricing page (0). Plan prices are public for Pro and Business, per member per month, with Enterprise through sales and no per-call price (10). A 30-day trial with no card is advertised. We scored it at half because the API needs a Business plan and we couldn't confirm that trial accounts can make tokens, and there's no free tier afterwards (10). A person signs up in a browser and creates the token or approves OAuth (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, 65 out of 100, up to 7 more on the total\n\nWhy it scored 65: Graded on the hosted API and MCP server. Statuspage at status.smartsheet.com with components for the REST API, Webhooks, Sheets and API Access Tokens (20). Ten incidents since 15 July 2026, eight marked major or critical. Post-incident reports put API timeouts at about five hours on 30 July, sheet and report failures on 11 August and 26 to 28 August, and a 51-minute US outage on 11 September (0). 300 requests a minute per token, 30 for attachments and cell history (15). Error 4003 on 429 with advice to wait 60 seconds or back off, and SDK retries, but no Retry-After header or idempotency keys documented (10). A 99.9 per cent SLA for Enterprise plans (10). GA, with no beta label on the API or the MCP server (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. Security \u0026 auth, 66 out of 100, up to 6 more on the total\n\nWhy it scored 66: OAuth 2.0 authorisation code grant with 17 scopes and tokens that expire in about 7 days. No PKCE or dynamic client registration appears in the docs or the server's OAuth metadata, and the raw API token most coding clients use has no scopes (22). READ_SHEETS gives a read-only grant and sharing levels cap what a token can touch. The MCP docs flag destructive tools and ask the agent to confirm, with no enforced approval step (12). Cells, comments and attachments are written by other people and no injection guidance was found (3). Activity log on Business and above, an Event Reporting API with over 100 event types, and a `smartsheet-integration-source` header that labels AI traffic (12). SOC 2, ISO 27001, ISO 27701, FedRAMP and a bug bounty form. security.txt expired on 1 July 2026 (17).\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. Agent ergonomics, 74 out of 100, up to 4.2 more on the total\n\nWhy it scored 74: The MCP reference lists 83 tools, which scores 5, plus 10 for toolsets with `search_tools` and a read or write filter. The API narrows a sheet read with columnIds, rowIds, rowsModifiedSince, include and exclude (15). Token and offset pagination, with unbounded includeAll results removed on 15 June 2026, and filters, sorting and column selection on `get_sheet_summary` (18). Numbered error codes with messages, and per-item failures on bulk writes (17). No idempotency keys. Partial success on bulk writes, a version check on sheet reads and separate read and write executors in MCP help. MCP annotations couldn't be read (9). Four official SDKs with retries built in, and few required parameters (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Schema \u0026 documentation, 88 out of 100, up to 2 more on the total\n\nWhy it scored 88: OpenAPI 3.0.3 spec with 187 operations, downloadable without login. The MCP docs describe the server as self-describing, which we couldn't confirm without an account (25). llms.txt and a Markdown copy of each docs page (10). The MCP reference gives each tool best practices, limitations and use cases, such as calling `get_columns` before filtering. We read the reference, not the live tool definitions (16). 472 schemas and 668 enums in the spec, though toolset executors take a tool name and a free-form arguments object (11). Code samples on 180 of 187 operations and a numbered error code page (14). Dated changelogs for the API and the MCP server. The API stays at 2.0 and changes arrive within that version (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## 6. Maintenance \u0026 community, 80 out of 100, up to 1.8 more on the total\n\nWhy it scored 80: API changelog entries on 2 and 6 October 2026 and MCP changelog entries on 2 October (30). Nine API and ten MCP changelog entries since 10 July 2026 (20). Closed service with dated changelogs, a developer community and a Stack Overflow tag. We didn't measure response times (10). SDKs for Python, JavaScript, Java and C# all released on 12 August 2026. The hosted MCP server isn't in the official MCP registry, where the only Smartsheet entry is a third-party Resource Management server (12). SDK repositories have CI workflows and commits in September and October 2026 (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## 7. Transparency \u0026 trust, 82 out of 100, up to 1.6 more on the total\n\nMade of editorial 72, provenance 92.\n\nWhy it scored 82: Closed service with a public User Agreement (3 April 2026) and Developer Agreement (1 July 2021). SDKs are Apache-2.0 (17). Privacy notice of 20 May 2026, a DPA built into the User Agreement, deletion of customer content within 180 days of termination, and a statement that customer data isn't used to train third-party foundation models. Personal data retention has no stated periods (22). A written deprecation process with DEPRECATION and SUNSET changelog entries, such as the `home` destination type ending on or after 30 October 2026, announced 22 September. No minimum notice period is promised (15). Sub-processor list with purposes, locations and a revision history, and US, EU and Australian regions (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- Terms of service: read, states 7 of the 7 things a reader expects, and has 1 clause that costs points (8 of 10)\n- Privacy policy: read, states 7 of the 8 things a reader expects (9.3 of 10)\n- security.txt: published but past its Expires date (5 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: the live MCP tool definitions, their JSON Schemas and any readOnlyHint or destructiveHint annotations. The server returns 401 without a token, so the tool count and descriptions come from the docs reference\n- unchecked: whether a 30-day trial account can create API tokens or connect to the MCP server\n- unchecked: the bug bounty's scope and rewards. The page is an embedded report form\n- Whether raw API tokens expire or can be limited by an admin. Not found in the reviewed documentation\n- Whether 429 responses carry a Retry-After header. The docs and the spec don't mention one\n- How quickly Smartsheet staff answer in the developer community. Not measured\n\n## Weaknesses\n\n- API and MCP access need a Business plan or higher, from $19 a member a month billed yearly with a three-member minimum\n- Eight status incidents marked major or critical between 15 July and 21 September 2026, four of them stopping sheets from loading in the US region\n- A raw API token carries all of its user's access with no scopes, and it's the credential the docs give for Claude Code, Cursor, Codex and Gemini CLI\n- No idempotency keys, and 429 responses carry no documented Retry-After header\n- security.txt expired on 1 July 2026, and no prompt-injection guidance was found in the MCP docs\n\n## What costs an agent a turn today\n\nThe notes we give agents before they call it. Each one is a workaround an agent shouldn't need.\n\n- Send writes to one sheet one at a time. Parallel updates with the same token return error 4004\n- Batch row changes, up to 500 rows a call, and add `allowPartialSuccess=true` to get per-row failures instead of a failed batch\n- On error 4003 (HTTP 429) wait at least 60 seconds before retrying. The limit is 300 requests a minute per token, 30 for attachments and cell history\n- Through MCP, call `get_columns` before filtering or writing. Column names are case-sensitive and guesses fail validation\n- Use the regional host that matches the account (api.smartsheet.com, .eu or .au). Tokens don't work across regions\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": 67.6,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 20,
        "maxGain": 10,
        "reason": "No x402, MPP or L402 found in the docs, the OpenAPI spec or the pricing page (0). Plan prices are public for Pro and Business, per member per month, with Enterprise through sales and no per-call price (10). A 30-day trial with no card is advertised. We scored it at half because the API needs a Business plan and we couldn't confirm that trial accounts can make tokens, and there's no free tier afterwards (10). A person signs up in a browser and creates the token or approves OAuth (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": 65,
        "maxGain": 7,
        "reason": "Graded on the hosted API and MCP server. Statuspage at status.smartsheet.com with components for the REST API, Webhooks, Sheets and API Access Tokens (20). Ten incidents since 15 July 2026, eight marked major or critical. Post-incident reports put API timeouts at about five hours on 30 July, sheet and report failures on 11 August and 26 to 28 August, and a 51-minute US outage on 11 September (0). 300 requests a minute per token, 30 for attachments and cell history (15). Error 4003 on 429 with advice to wait 60 seconds or back off, and SDK retries, but no Retry-After header or idempotency keys documented (10). A 99.9 per cent SLA for Enterprise plans (10). GA, with no beta label on the API or the MCP server (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": "security",
        "name": "Security \u0026 auth",
        "score": 66,
        "maxGain": 6,
        "reason": "OAuth 2.0 authorisation code grant with 17 scopes and tokens that expire in about 7 days. No PKCE or dynamic client registration appears in the docs or the server's OAuth metadata, and the raw API token most coding clients use has no scopes (22). READ_SHEETS gives a read-only grant and sharing levels cap what a token can touch. The MCP docs flag destructive tools and ask the agent to confirm, with no enforced approval step (12). Cells, comments and attachments are written by other people and no injection guidance was found (3). Activity log on Business and above, an Event Reporting API with over 100 event types, and a `smartsheet-integration-source` header that labels AI traffic (12). SOC 2, ISO 27001, ISO 27701, FedRAMP and a bug bounty form. security.txt expired on 1 July 2026 (17).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 74,
        "maxGain": 4.2,
        "reason": "The MCP reference lists 83 tools, which scores 5, plus 10 for toolsets with `search_tools` and a read or write filter. The API narrows a sheet read with columnIds, rowIds, rowsModifiedSince, include and exclude (15). Token and offset pagination, with unbounded includeAll results removed on 15 June 2026, and filters, sorting and column selection on `get_sheet_summary` (18). Numbered error codes with messages, and per-item failures on bulk writes (17). No idempotency keys. Partial success on bulk writes, a version check on sheet reads and separate read and write executors in MCP help. MCP annotations couldn't be read (9). Four official SDKs with retries built in, and few required parameters (15).",
        "checklist": [
          "- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.",
          "Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-ergonomics"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 88,
        "maxGain": 2,
        "reason": "OpenAPI 3.0.3 spec with 187 operations, downloadable without login. The MCP docs describe the server as self-describing, which we couldn't confirm without an account (25). llms.txt and a Markdown copy of each docs page (10). The MCP reference gives each tool best practices, limitations and use cases, such as calling `get_columns` before filtering. We read the reference, not the live tool definitions (16). 472 schemas and 668 enums in the spec, though toolset executors take a tool name and a free-form arguments object (11). Code samples on 180 of 187 operations and a numbered error code page (14). Dated changelogs for the API and the MCP server. The API stays at 2.0 and changes arrive within that version (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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 80,
        "maxGain": 1.8,
        "reason": "API changelog entries on 2 and 6 October 2026 and MCP changelog entries on 2 October (30). Nine API and ten MCP changelog entries since 10 July 2026 (20). Closed service with dated changelogs, a developer community and a Stack Overflow tag. We didn't measure response times (10). SDKs for Python, JavaScript, Java and C# all released on 12 August 2026. The hosted MCP server isn't in the official MCP registry, where the only Smartsheet entry is a third-party Resource Management server (12). SDK repositories have CI workflows and commits in September and October 2026 (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 82,
        "maxGain": 1.6,
        "reason": "Closed service with a public User Agreement (3 April 2026) and Developer Agreement (1 July 2021). SDKs are Apache-2.0 (17). Privacy notice of 20 May 2026, a DPA built into the User Agreement, deletion of customer content within 180 days of termination, and a statement that customer data isn't used to train third-party foundation models. Personal data retention has no stated periods (22). A written deprecation process with DEPRECATION and SUNSET changelog entries, such as the `home` destination type ending on or after 30 October 2026, announced 22 September. No minimum notice period is promised (15). Sub-processor list with purposes, locations and a revision history, and US, EU and Australian regions (18).",
        "blend": "editorial 72, provenance 92",
        "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": "Terms of service",
        "value": "read, states 7 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 8,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 7 of the 8 things a reader expects",
        "points": 9.3,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "published but past its Expires date",
        "points": 5,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: the live MCP tool definitions, their JSON Schemas and any readOnlyHint or destructiveHint annotations. The server returns 401 without a token, so the tool count and descriptions come from the docs reference",
      "unchecked: whether a 30-day trial account can create API tokens or connect to the MCP server",
      "unchecked: the bug bounty's scope and rewards. The page is an embedded report form",
      "Whether raw API tokens expire or can be limited by an admin. Not found in the reviewed documentation",
      "Whether 429 responses carry a Retry-After header. The docs and the spec don't mention one",
      "How quickly Smartsheet staff answer in the developer community. Not measured"
    ],
    "weaknesses": [
      "API and MCP access need a Business plan or higher, from $19 a member a month billed yearly with a three-member minimum",
      "Eight status incidents marked major or critical between 15 July and 21 September 2026, four of them stopping sheets from loading in the US region",
      "A raw API token carries all of its user's access with no scopes, and it's the credential the docs give for Claude Code, Cursor, Codex and Gemini CLI",
      "No idempotency keys, and 429 responses carry no documented Retry-After header",
      "security.txt expired on 1 July 2026, and no prompt-injection guidance was found in the MCP docs"
    ],
    "agentNotes": [
      "Send writes to one sheet one at a time. Parallel updates with the same token return error 4004",
      "Batch row changes, up to 500 rows a call, and add `allowPartialSuccess=true` to get per-row failures instead of a failed batch",
      "On error 4003 (HTTP 429) wait at least 60 seconds before retrying. The limit is 300 requests a minute per token, 30 for attachments and cell history",
      "Through MCP, call `get_columns` before filtering or writing. Column names are case-sensitive and guesses fail validation",
      "Use the regional host that matches the account (api.smartsheet.com, .eu or .au). Tokens don't work across regions"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}