{
  "fixes": {
    "slug": "1password",
    "name": "1Password service accounts, SDKs and Environments MCP",
    "listing": "https://www.anchorterminal.com/tools/1password",
    "markdown": "# Fix list: 1Password service accounts, SDKs and Environments MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/1password, the October 2026 research run, assessed 1 October 2026. Grade B, 69.9 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 1Password service accounts, SDKs and Environments 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 (0). Plan prices are public, with no per-call pricing (10). A 14-day trial on every plan, and the pricing pages don't say whether a card is needed, so half (10 of 20). A person signs up in a browser and creates the service account, and there's no API to create one without a signed-in human (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, 68 out of 100, up to 6.4 more on the total\n\nWhy it scored 68: Atlassian Statuspage at status.1password.com with per-region components for CLI, Connect, Service Accounts and the Events API (20). Since 3 July 2026 the history shows six incidents, on Device Trust (2 July, about 45 minutes, and 9 September, about 30), SaaS Manager (17 and 22 July), account management for personal plans (13 July, about an hour) and the update server that GitHub Actions pulls the CLI from (13 July). None was posted against service accounts or Connect, so minor only (20). Rate limits published per token and per account for every plan (15). The 429 messages are documented, but there's no Retry-After or backoff guidance, only a note to wait for the window or upgrade (8 of 15). No SLA found for any plan (0). Service accounts, the CLI and Environments are generally available, while the SDKs are version 0 and the MCP server is beta (5 of 10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):\n\nHosted APIs, MCP servers, models and platforms.\n\n- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.\n\nLocal packages, SDKs, frameworks and stdio MCP servers.\n\n- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.\n\nProtocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors.\n\n## 3. Agent ergonomics, 69 out of 100, up to 5 more on the total\n\nWhy it scored 69: The MCP server has 8 tools and returns names only, but its definitions aren't published, so we can't size them (20 of 25). Connect filters items with SCIM-style title and tag filters and pages the activity log, while the SDK lists vaults and items by state without paging (12 of 20). Errors carry a status and message in Connect and fixed 429 texts for service accounts, and issues #243 and #218 in the Python SDK report vague or misleading exceptions (10 of 20). The docs mark 4 MCP tools read-only and 4 destructive, and secret reads are safe to repeat, but there's no idempotency for writes (12 of 20). Official Go, JavaScript and Python SDKs, op:// references as the only required input for a read (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## 4. Schema \u0026 documentation, 74 out of 100, up to 4.2 more on the total\n\nWhy it scored 74: No contract for the service account path itself, but the self-hosted Connect server has a public OpenAPI file (1.8.1), and the MCP tools are closed source so their schemas can't be read (15 of 25). llms.txt at www.1password.dev with Markdown links for service accounts, SDKs, Connect, the Events API, the CLI and the MCP server (10). The docs say what each piece is for and the AI agent tutorial says when not to use it (12 of 20). The SDKs are typed in TypeScript, Go and Python and the Connect spec types every field (12 of 15). Plenty of examples, a documented Connect error body and the 429 texts, but SDK errors are thin and two open issues ask for better exceptions (10 of 15). Dated release notes for the SDKs, CLI and Connect at releases.1password.com (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## 5. Maintenance \u0026 community, 72 out of 100, up to 2.5 more on the total\n\nWhy it scored 72: CLI 2.39.0 on 14 August 2026 and JavaScript SDK 0.5.0 on 31 July 2026, so the newest release is 48 days old (20). CLI 2.35.0, 2.38.1 and 2.39.0 and SDK 0.4.1 and 0.5.0 all fall in the last 90 days (20). The JavaScript SDK has 30 open issues and 16 open pull requests, and in the Python SDK 5 of the 8 newest open issues have no reply, including a broken get_variables report from 3 June 2026 (10 of 25). Current official SDKs in three languages; nothing in the MCP registry under a 1Password namespace (15). The SDKs pin one current core package, and CPython 3.14 wheels are still an open request (7 of 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## 6. Security \u0026 auth, 94 out of 100, up to 1.1 more on the total\n\nWhy it scored 94: Service account tokens are scoped per vault to read_items, write_items or share_items, can expire with --expires-in, are revocable, and permissions can't be widened after creation. The JavaScript SDK 0.5.0 adds workload identity through the Credential Broker in public preview (30). Read-only service accounts, Personal, Private and Employee vaults excluded, and the MCP server asks for approval per Environment in the desktop app, though not per destructive call (17 of 20). The MCP server won't return a secret value even when asked, and the SDK agent tutorial warns against putting raw credentials in front of a model (15). Service account usage reports show which items were read, and the audit log and Events API need Business (12 of 15). security.txt with a HackerOne programme, a public trust centre listing SOC 2 Type II and ISO 27001 (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-security):\n\n- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.\n\nModels are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing.\n\n## 7. Transparency \u0026 trust, 89 out of 100, up to 1 more on the total\n\nMade of editorial 78, provenance 100.\n\nWhy it scored 89: SDK wrappers and the WebAssembly core package are MIT, the CLI, desktop app and service are closed under clear terms (18 of 30). Privacy notice effective 29 December 2025, a DPA (v202504) and a subprocessor list effective 30 April 2025 agree, though retention is only as long as necessary (25 of 30). SDK support policy of three months of patches per version 0 release, with dated release notes (15 of 20). Subprocessors listed and data hosted in the US, Canada or EU at the customer's choice (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\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- Whether the 14-day trial needs a card; the pricing pages don't say, and the listing's card-required tag is unconfirmed.\n- The listing's MCP config runs a 1password-mcp command; we couldn't confirm that binary name from the MCP server page.\n- Whether service account usage reports are available on Teams or only Business.\n- The status page uptime percentages, which our fetch didn't show.\n\n## Weaknesses\n\n- Teams, Families and Individual get 1,000 service account reads an hour per token, and the 429 carries no Retry-After\n- SDKs are version 0 with three months of patches per release, and 5 of the 8 newest Python SDK issues have no reply\n- No SLA found, and the audit log and Events API need Business\n- The MCP server is beta and needs the desktop app running and unlocked, so it's for a developer's machine, not a server\n- No MCP registry entry and no way to create a service account without a signed-in person\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- Read secrets by reference (op://vault/item/field) with client.secrets.resolve or resolveAll, and keep the reference, not the value, in config\n- On Teams or personal plans budget for 1,000 reads an hour per token and cache resolved values for the run; a 429 means wait for the hourly window, there's no Retry-After\n- Create the service account with only read_items on one vault and --expires-in set to the job length, since permissions can't be narrowed later\n- Set integrationName and integrationVersion in createClient so the usage report shows which agent read what\n- Don't ask the Environments MCP server for a value. Use it to find the variable name, then load it with op run or the SDK\n\n## What the review panel asked for\n\n- semver 1.0 SDKs\n- a longer patch window\n- per-call approval on destructive tools\n- audit log below Business\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": 69.9,
    "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). Plan prices are public, with no per-call pricing (10). A 14-day trial on every plan, and the pricing pages don't say whether a card is needed, so half (10 of 20). A person signs up in a browser and creates the service account, and there's no API to create one without a signed-in human (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": 68,
        "maxGain": 6.4,
        "reason": "Atlassian Statuspage at status.1password.com with per-region components for CLI, Connect, Service Accounts and the Events API (20). Since 3 July 2026 the history shows six incidents, on Device Trust (2 July, about 45 minutes, and 9 September, about 30), SaaS Manager (17 and 22 July), account management for personal plans (13 July, about an hour) and the update server that GitHub Actions pulls the CLI from (13 July). None was posted against service accounts or Connect, so minor only (20). Rate limits published per token and per account for every plan (15). The 429 messages are documented, but there's no Retry-After or backoff guidance, only a note to wait for the window or upgrade (8 of 15). No SLA found for any plan (0). Service accounts, the CLI and Environments are generally available, while the SDKs are version 0 and the MCP server is beta (5 of 10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 69,
        "maxGain": 5,
        "reason": "The MCP server has 8 tools and returns names only, but its definitions aren't published, so we can't size them (20 of 25). Connect filters items with SCIM-style title and tag filters and pages the activity log, while the SDK lists vaults and items by state without paging (12 of 20). Errors carry a status and message in Connect and fixed 429 texts for service accounts, and issues #243 and #218 in the Python SDK report vague or misleading exceptions (10 of 20). The docs mark 4 MCP tools read-only and 4 destructive, and secret reads are safe to repeat, but there's no idempotency for writes (12 of 20). Official Go, JavaScript and Python SDKs, op:// references as the only required input for a read (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": 74,
        "maxGain": 4.2,
        "reason": "No contract for the service account path itself, but the self-hosted Connect server has a public OpenAPI file (1.8.1), and the MCP tools are closed source so their schemas can't be read (15 of 25). llms.txt at www.1password.dev with Markdown links for service accounts, SDKs, Connect, the Events API, the CLI and the MCP server (10). The docs say what each piece is for and the AI agent tutorial says when not to use it (12 of 20). The SDKs are typed in TypeScript, Go and Python and the Connect spec types every field (12 of 15). Plenty of examples, a documented Connect error body and the 429 texts, but SDK errors are thin and two open issues ask for better exceptions (10 of 15). Dated release notes for the SDKs, CLI and Connect at releases.1password.com (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": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 72,
        "maxGain": 2.5,
        "reason": "CLI 2.39.0 on 14 August 2026 and JavaScript SDK 0.5.0 on 31 July 2026, so the newest release is 48 days old (20). CLI 2.35.0, 2.38.1 and 2.39.0 and SDK 0.4.1 and 0.5.0 all fall in the last 90 days (20). The JavaScript SDK has 30 open issues and 16 open pull requests, and in the Python SDK 5 of the 8 newest open issues have no reply, including a broken get_variables report from 3 June 2026 (10 of 25). Current official SDKs in three languages; nothing in the MCP registry under a 1Password namespace (15). The SDKs pin one current core package, and CPython 3.14 wheels are still an open request (7 of 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": "security",
        "name": "Security \u0026 auth",
        "score": 94,
        "maxGain": 1.1,
        "reason": "Service account tokens are scoped per vault to read_items, write_items or share_items, can expire with --expires-in, are revocable, and permissions can't be widened after creation. The JavaScript SDK 0.5.0 adds workload identity through the Credential Broker in public preview (30). Read-only service accounts, Personal, Private and Employee vaults excluded, and the MCP server asks for approval per Environment in the desktop app, though not per destructive call (17 of 20). The MCP server won't return a secret value even when asked, and the SDK agent tutorial warns against putting raw credentials in front of a model (15). Service account usage reports show which items were read, and the audit log and Events API need Business (12 of 15). security.txt with a HackerOne programme, a public trust centre listing SOC 2 Type II and ISO 27001 (20).",
        "checklist": [
          "- 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option.\n- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.\n- 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10.\n- 0 to 15, audit logs or per-call visibility for the operator.\n- 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public.",
          "Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-security"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 89,
        "maxGain": 1,
        "reason": "SDK wrappers and the WebAssembly core package are MIT, the CLI, desktop app and service are closed under clear terms (18 of 30). Privacy notice effective 29 December 2025, a DPA (v202504) and a subprocessor list effective 30 April 2025 agree, though retention is only as long as necessary (25 of 30). SDK support policy of three months of patches per version 0 release, with dated release notes (15 of 20). Subprocessors listed and data hosted in the US, Canada or EU at the customer's choice (20).",
        "blend": "editorial 78, provenance 100",
        "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"
      }
    ],
    "unchecked": [
      "Whether the 14-day trial needs a card; the pricing pages don't say, and the listing's card-required tag is unconfirmed.",
      "The listing's MCP config runs a 1password-mcp command; we couldn't confirm that binary name from the MCP server page.",
      "Whether service account usage reports are available on Teams or only Business.",
      "The status page uptime percentages, which our fetch didn't show."
    ],
    "weaknesses": [
      "Teams, Families and Individual get 1,000 service account reads an hour per token, and the 429 carries no Retry-After",
      "SDKs are version 0 with three months of patches per release, and 5 of the 8 newest Python SDK issues have no reply",
      "No SLA found, and the audit log and Events API need Business",
      "The MCP server is beta and needs the desktop app running and unlocked, so it's for a developer's machine, not a server",
      "No MCP registry entry and no way to create a service account without a signed-in person"
    ],
    "agentNotes": [
      "Read secrets by reference (op://vault/item/field) with client.secrets.resolve or resolveAll, and keep the reference, not the value, in config",
      "On Teams or personal plans budget for 1,000 reads an hour per token and cache resolved values for the run; a 429 means wait for the hourly window, there's no Retry-After",
      "Create the service account with only read_items on one vault and --expires-in set to the job length, since permissions can't be narrowed later",
      "Set integrationName and integrationVersion in createClient so the usage report shows which agent read what",
      "Don't ask the Environments MCP server for a value. Use it to find the variable name, then load it with op run or the SDK"
    ],
    "requests": [
      {
        "text": "semver 1.0 SDKs",
        "reviews": 1
      },
      {
        "text": "a longer patch window",
        "reviews": 1
      },
      {
        "text": "per-call approval on destructive tools",
        "reviews": 1
      },
      {
        "text": "audit log below Business",
        "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"
  }
}