{
  "fixes": {
    "slug": "stackone",
    "name": "StackOne",
    "listing": "https://www.anchorterminal.com/tools/stackone",
    "markdown": "# Fix list: StackOne\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/stackone, the October 2026 research run, assessed 9 October 2026. Grade B, 69.1 out of 100.\n\nThis is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public.\n\nFor a coding agent working on StackOne: 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, 38 out of 100, up to 7.8 more on the total\n\nWhy it scored 38: No x402, MPP or L402 (0). Credit prices are public. One credit per tool call or API call, extra credits at $60 per 20,000 on Starter and $20 per 20,000 on Team, and Team at $600 a month. Two off because the per-seat price sits only in the calculator's markup, the rates for advanced capabilities aren't published, and the Service Consumption Schedule and the pricing page disagree on failed calls (18). Free plans on both models with no card, per the pricing page (20). A person signs up in the dashboard, and no keyless or programmatic signup route was found (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. Security \u0026 auth, 69 out of 100, up to 5.4 more on the total\n\nWhy it scored 69: OAuth per user with one-hour access tokens, a 90-day grant and revocation, and project API keys with scopes that can be disabled or deleted, would score 30. Ten off because session token URLs carry the access in the query string as a documented option, with a one-year default expiry (20). Connector profiles enable individual actions, users grant accounts and actions at consent, the Credentials scope is off by default, and Policies deny tools, mask fields and bound values on Team and Enterprise. Policies skip API-key calls, and no approval step at the gateway was found (16). Defender scans tool results and is on for new projects, in Monitor mode by default, which changes nothing. Large responses skip scanning by default (12). Action logs on every plan (one day on Starter), login security logs and Advanced Logs with credential masking. The Logs API, audit logs and SIEM export are Enterprise only on Gateway plans (11). SOC 2 Type II and HIPAA are stated on the pricing and contact pages, and the DPA promises breach notice within 48 hours. security.txt returned 404, no bounty or disclosure policy was found, and the trust centre answered with a bot check (10).\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## 3. Agent ergonomics, 75 out of 100, up to 4.1 more on the total\n\nWhy it scored 75: The catalogue is large, and `individual` mode registers one tool per enabled action, which scores 5. Ten back for the two-tool search and execute mode (on by default at the OAuth consent screen), per-action grants and connector profile scoping (15). List endpoints take `page` and `page_size` with a total, filters and field expansion, tool search takes `top_k`, and Deep Query returns counts or chosen fields. Offset paging can skip or repeat records, as the docs warn (16). Errors carry `statusCode`, `errorCode`, `details.statusReasons` and provider errors, with documented causes for 400, 401, 406, 412 and the JSON-RPC codes (17). Every tool carries `readOnlyHint` and `destructiveHint` since July 2026. `idempotentHint` is set only by hand and tool calls take no idempotency key (14). Agent SDKs for TypeScript and Python and API clients in five languages. The mandatory `Accept` header and Basic auth encoding are extra steps (13).\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. Reliability, 80 out of 100, up to 4 more on the total\n\nWhy it scored 80: Read with the hosted lines. status.stackone.com on incident.io lists the Web Dashboard, the API in three regions and the Connectors Hub (20). The page shows July to October 2026 at 100 per cent for the dashboard, the hub and the US and UK API, and 99.990 per cent for the EU API. The incident list is drawn by script and was not read, so 20 of 30 (20). API keys are limited to 1,000 requests a minute (15). 429 responses carry `Retry-After` in seconds, and StackOne retries a provider's 429 up to five times within a 60-second request lifetime before returning 429 or 408. No idempotency key or retry guidance for writes was found (10). The pricing page lists an uptime SLA on Enterprise with no figure, and the Starter plan has none (5). MCP and the RPC endpoint carry no beta label. A2A is in open beta (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## 5. Schema \u0026 documentation, 78 out of 100, up to 3.6 more on the total\n\nWhy it scored 78: An OpenAPI 3.1 file is published for the Platform API (30 operations under `/v2`), the actions, logs and MCP endpoints have reference pages with embedded definitions, and the docs say each MCP tool has a JSON Schema. Live tool schemas were not read, since that needs an account (22). llms.txt for the docs and the site, and a Markdown twin of every docs page (10). Connector pages give one line per action, such as 'Send a message to a channel or conversation', with the provider scopes each needs and no guidance on when not to use it (11). The Platform API types its parameters and has 26 enum uses, while `POST /actions/rpc` and the execute tool take open `path`, `query`, `body` and `headers` objects (9). curl, Python and TypeScript examples, eleven error statuses declared on every operation and a troubleshooting catalogue for MCP (13). `/v2` paths, connector semver with version pins, per-connector changelogs and a dated product changelog. No API deprecation policy was found (13).\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. Transparency \u0026 trust, 69 out of 100, up to 2.7 more on the total\n\nMade of editorial 50, provenance 88.\n\nWhy it scored 69: The editorial half. Closed service under SaaS terms that name StackOne Technologies Limited, with the Agent SDKs and Defender under Apache-2.0 (17). The DPA of 15 January 2025 promises deletion within 30 days of termination and breach notice within 48 hours, and the AI Services Addendum says AI providers may not train on customer data. The privacy policy of December 2023 says data is stored in the EEA while projects can be created in a US region, and it gives 30 and 90 day retention periods side by side. The SaaS terms let StackOne use anonymised usage data to improve the Service (18). No deprecation policy for the API was found. Preview functions can be withdrawn at any time, and the Starter plan can change with 30 days' notice on a reasonable-efforts basis. Connector versions can be pinned (5). Three hosting regions are named with their data centres. The sub-processor list is on the trust centre, which we could not read. The DPA gives 14 days to object to a new sub-processor (10).\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 6 of the 7 things a reader expects (9.1 of 10)\n- Privacy policy: read, states 6 of the 8 things a reader expects (8.5 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Maintenance \u0026 community, 84 out of 100, up to 1.4 more on the total\n\nWhy it scored 84: Changelog entry on 24 September 2026 (Deep Query) and `@stackone/defender` v0.8.3 on 23 September (30). Dated entries on 24 July, 3, 7 and 19 August, and 7 and 24 September (20). A closed service with a dated changelog and in-app chat and email support. The TypeScript SDK repository shows 7 open issues and commits on 9 October 2026 (11). `com.stackone/mcp` is in the official MCP registry under the vendor's domain namespace, version 1.0.1 of 17 August 2026 (15). The SDK repositories carry CI workflows, lockfiles and release automation. The newest Agent SDK releases are from late July (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## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- 27 April 2026. `@stackone/ai` v2.8.1 fixed a flaw in which tools fetched concurrently for several accounts were stamped with the wrong `x-account-id`, so a call could run against another linked account. It is recorded as a bug fix in the changelog, with no advisory found. Fixed and documented, so 2 points (https://github.com/StackOneHQ/stackone-ai-node/blob/main/CHANGELOG.md).\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: trust.stackone.com (security policy, sub-processor list, certifications, any disclosure programme), which answered our reader with a bot check. We did not retry\n- unchecked: the incident list on status.stackone.com, which is drawn by script. Only the component uptime figures were read\n- unchecked: live tool definitions from `tools/list`, including the size of schemas and the annotations, because reading them needs an account and we did not create one\n- unchecked: api.stackone.com and mcp.stackone.com answered 403 to a robots.txt request, so no further request was sent to either, and the OAuth metadata was not read\n- unchecked: weekly downloads of `stackone-ai` on PyPI\n- Whether failed calls are billed. The pricing page says no and the Service Consumption Schedule counts them\n- The credit cost of browser use, premium defence and data sync, and the figure in the Enterprise uptime SLA\n- Whether the seat prices in the pricing calculator's markup ($15 a further seat on Team, 10 included) are what a customer is charged\n- Whether the Platform Privacy Policy of December 2023, which says data is stored in the EEA, still describes projects created in the US region\n- The Acceptable Use Policy bars benchmarking other than for internal comparison and vulnerability testing without authorisation, which matters before any probe is run\n\n## Weaknesses\n\n- Session token URLs (`https://api.stackone.com/mcp?token=...`) put the credential in the query string, cover one linked account and expire after one year by default\n- The Service Consumption Schedule counts every request, successful or not, as an Action Call. The pricing page says failed calls aren't billed\n- Defender's default mode is Monitor, which records a verdict and passes the tool result to the agent unchanged\n- Policies apply only to signed-in members. A call made with a project API key is memberless and is governed by connector profile scoping alone\n- The Logs API, audit logs, SIEM export and an uptime SLA are Enterprise only on Gateway plans, and Starter keeps action logs for one day\n- The Acceptable Use Policy bars competitive analysis or benchmarking other than for internal comparison, and probing or testing the Service's vulnerability without authorisation. This matters before any probe is run\n- `@stackone/ai` stamped tools with the wrong `x-account-id` when accounts were fetched concurrently, until v2.8.1 on 27 April 2026. No advisory was found\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 `Accept: application/json,text/event-stream` on every MCP request to `https://api.stackone.com/mcp`, by POST only. Without it the server answers 406\n- In `search_execute` mode call `{provider}_search_actions` first and pass the returned `action_id` to `{provider}_execute_action`. Never hardcode action ids\n- Pass the API key as the Basic auth username with an empty password, and name the linked account in `x-account-id`\n- On 429 or 408 wait the seconds given in `Retry-After`. StackOne has already retried a provider's 429 up to five times within a 60-second request lifetime\n- On 412 read `errorCode` and `details.statusReasons`. `AccountErrorStatus` needs a person to re-authenticate the linked account\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": 69.1,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 38,
        "maxGain": 7.8,
        "reason": "No x402, MPP or L402 (0). Credit prices are public. One credit per tool call or API call, extra credits at $60 per 20,000 on Starter and $20 per 20,000 on Team, and Team at $600 a month. Two off because the per-seat price sits only in the calculator's markup, the rates for advanced capabilities aren't published, and the Service Consumption Schedule and the pricing page disagree on failed calls (18). Free plans on both models with no card, per the pricing page (20). A person signs up in the dashboard, and no keyless or programmatic signup route was found (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": "security",
        "name": "Security \u0026 auth",
        "score": 69,
        "maxGain": 5.4,
        "reason": "OAuth per user with one-hour access tokens, a 90-day grant and revocation, and project API keys with scopes that can be disabled or deleted, would score 30. Ten off because session token URLs carry the access in the query string as a documented option, with a one-year default expiry (20). Connector profiles enable individual actions, users grant accounts and actions at consent, the Credentials scope is off by default, and Policies deny tools, mask fields and bound values on Team and Enterprise. Policies skip API-key calls, and no approval step at the gateway was found (16). Defender scans tool results and is on for new projects, in Monitor mode by default, which changes nothing. Large responses skip scanning by default (12). Action logs on every plan (one day on Starter), login security logs and Advanced Logs with credential masking. The Logs API, audit logs and SIEM export are Enterprise only on Gateway plans (11). SOC 2 Type II and HIPAA are stated on the pricing and contact pages, and the DPA promises breach notice within 48 hours. security.txt returned 404, no bounty or disclosure policy was found, and the trust centre answered with a bot check (10).",
        "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": 75,
        "maxGain": 4.1,
        "reason": "The catalogue is large, and `individual` mode registers one tool per enabled action, which scores 5. Ten back for the two-tool search and execute mode (on by default at the OAuth consent screen), per-action grants and connector profile scoping (15). List endpoints take `page` and `page_size` with a total, filters and field expansion, tool search takes `top_k`, and Deep Query returns counts or chosen fields. Offset paging can skip or repeat records, as the docs warn (16). Errors carry `statusCode`, `errorCode`, `details.statusReasons` and provider errors, with documented causes for 400, 401, 406, 412 and the JSON-RPC codes (17). Every tool carries `readOnlyHint` and `destructiveHint` since July 2026. `idempotentHint` is set only by hand and tool calls take no idempotency key (14). Agent SDKs for TypeScript and Python and API clients in five languages. The mandatory `Accept` header and Basic auth encoding are extra steps (13).",
        "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": "reliability",
        "name": "Reliability",
        "score": 80,
        "maxGain": 4,
        "reason": "Read with the hosted lines. status.stackone.com on incident.io lists the Web Dashboard, the API in three regions and the Connectors Hub (20). The page shows July to October 2026 at 100 per cent for the dashboard, the hub and the US and UK API, and 99.990 per cent for the EU API. The incident list is drawn by script and was not read, so 20 of 30 (20). API keys are limited to 1,000 requests a minute (15). 429 responses carry `Retry-After` in seconds, and StackOne retries a provider's 429 up to five times within a 60-second request lifetime before returning 429 or 408. No idempotency key or retry guidance for writes was found (10). The pricing page lists an uptime SLA on Enterprise with no figure, and the Starter plan has none (5). MCP and the RPC endpoint carry no beta label. A2A is in open beta (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": "schema",
        "name": "Schema \u0026 documentation",
        "score": 78,
        "maxGain": 3.6,
        "reason": "An OpenAPI 3.1 file is published for the Platform API (30 operations under `/v2`), the actions, logs and MCP endpoints have reference pages with embedded definitions, and the docs say each MCP tool has a JSON Schema. Live tool schemas were not read, since that needs an account (22). llms.txt for the docs and the site, and a Markdown twin of every docs page (10). Connector pages give one line per action, such as 'Send a message to a channel or conversation', with the provider scopes each needs and no guidance on when not to use it (11). The Platform API types its parameters and has 26 enum uses, while `POST /actions/rpc` and the execute tool take open `path`, `query`, `body` and `headers` objects (9). curl, Python and TypeScript examples, eleven error statuses declared on every operation and a troubleshooting catalogue for MCP (13). `/v2` paths, connector semver with version pins, per-connector changelogs and a dated product changelog. No API deprecation policy was found (13).",
        "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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 69,
        "maxGain": 2.7,
        "reason": "The editorial half. Closed service under SaaS terms that name StackOne Technologies Limited, with the Agent SDKs and Defender under Apache-2.0 (17). The DPA of 15 January 2025 promises deletion within 30 days of termination and breach notice within 48 hours, and the AI Services Addendum says AI providers may not train on customer data. The privacy policy of December 2023 says data is stored in the EEA while projects can be created in a US region, and it gives 30 and 90 day retention periods side by side. The SaaS terms let StackOne use anonymised usage data to improve the Service (18). No deprecation policy for the API was found. Preview functions can be withdrawn at any time, and the Starter plan can change with 30 days' notice on a reasonable-efforts basis. Connector versions can be pinned (5). Three hosting regions are named with their data centres. The sub-processor list is on the trust centre, which we could not read. The DPA gives 14 days to object to a new sub-processor (10).",
        "blend": "editorial 50, provenance 88",
        "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": 84,
        "maxGain": 1.4,
        "reason": "Changelog entry on 24 September 2026 (Deep Query) and `@stackone/defender` v0.8.3 on 23 September (30). Dated entries on 24 July, 3, 7 and 19 August, and 7 and 24 September (20). A closed service with a dated changelog and in-app chat and email support. The TypeScript SDK repository shows 7 open issues and commits on 9 October 2026 (11). `com.stackone/mcp` is in the official MCP registry under the vendor's domain namespace, version 1.0.1 of 17 August 2026 (15). The SDK repositories carry CI workflows, lockfiles and release automation. The newest Agent SDK releases are from late July (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"
      }
    ],
    "provenance": [
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects",
        "points": 9.1,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "read, states 6 of the 8 things a reader expects",
        "points": 8.5,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "27 April 2026. `@stackone/ai` v2.8.1 fixed a flaw in which tools fetched concurrently for several accounts were stamped with the wrong `x-account-id`, so a call could run against another linked account. It is recorded as a bug fix in the changelog, with no advisory found. Fixed and documented, so 2 points (https://github.com/StackOneHQ/stackone-ai-node/blob/main/CHANGELOG.md)."
    ],
    "unchecked": [
      "unchecked: trust.stackone.com (security policy, sub-processor list, certifications, any disclosure programme), which answered our reader with a bot check. We did not retry",
      "unchecked: the incident list on status.stackone.com, which is drawn by script. Only the component uptime figures were read",
      "unchecked: live tool definitions from `tools/list`, including the size of schemas and the annotations, because reading them needs an account and we did not create one",
      "unchecked: api.stackone.com and mcp.stackone.com answered 403 to a robots.txt request, so no further request was sent to either, and the OAuth metadata was not read",
      "unchecked: weekly downloads of `stackone-ai` on PyPI",
      "Whether failed calls are billed. The pricing page says no and the Service Consumption Schedule counts them",
      "The credit cost of browser use, premium defence and data sync, and the figure in the Enterprise uptime SLA",
      "Whether the seat prices in the pricing calculator's markup ($15 a further seat on Team, 10 included) are what a customer is charged",
      "Whether the Platform Privacy Policy of December 2023, which says data is stored in the EEA, still describes projects created in the US region",
      "The Acceptable Use Policy bars benchmarking other than for internal comparison and vulnerability testing without authorisation, which matters before any probe is run"
    ],
    "weaknesses": [
      "Session token URLs (`https://api.stackone.com/mcp?token=...`) put the credential in the query string, cover one linked account and expire after one year by default",
      "The Service Consumption Schedule counts every request, successful or not, as an Action Call. The pricing page says failed calls aren't billed",
      "Defender's default mode is Monitor, which records a verdict and passes the tool result to the agent unchanged",
      "Policies apply only to signed-in members. A call made with a project API key is memberless and is governed by connector profile scoping alone",
      "The Logs API, audit logs, SIEM export and an uptime SLA are Enterprise only on Gateway plans, and Starter keeps action logs for one day",
      "The Acceptable Use Policy bars competitive analysis or benchmarking other than for internal comparison, and probing or testing the Service's vulnerability without authorisation. This matters before any probe is run",
      "`@stackone/ai` stamped tools with the wrong `x-account-id` when accounts were fetched concurrently, until v2.8.1 on 27 April 2026. No advisory was found"
    ],
    "agentNotes": [
      "Send `Accept: application/json,text/event-stream` on every MCP request to `https://api.stackone.com/mcp`, by POST only. Without it the server answers 406",
      "In `search_execute` mode call `{provider}_search_actions` first and pass the returned `action_id` to `{provider}_execute_action`. Never hardcode action ids",
      "Pass the API key as the Basic auth username with an empty password, and name the linked account in `x-account-id`",
      "On 429 or 408 wait the seconds given in `Retry-After`. StackOne has already retried a provider's 429 up to five times within a 60-second request lifetime",
      "On 412 read `errorCode` and `details.statusReasons`. `AccountErrorStatus` needs a person to re-authenticate the linked account"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-10",
    "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"
  }
}