{
  "fixes": {
    "slug": "one",
    "name": "One",
    "listing": "https://www.anchorterminal.com/tools/one",
    "markdown": "# Fix list: One\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/one, the October 2026 research run, assessed 9 October 2026. Grade B, 66.6 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 One: 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, 30 out of 100, up to 8.8 more on the total\n\nWhy it scored 30: No x402, MPP or L402 (0). Plan prices are public with their limits, $0, $29 and $199 a month, and nothing is billed over the limit. There is no per-call price and Enterprise is on contract, so 15 of 20 (15). The Free plan includes every platform and 1M requests a month. The pricing page doesn't say whether sign-up needs a card and we did not create an account, so 15 of 20 (15). A person must sign in through a browser to approve the grant or create an API key (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 2.1 authorisation code with PKCE, scopes, one-hour access tokens, and a grant that can be narrowed or revoked from the dashboard with effect on the next call (30). Read only, Read \u0026 write, Full access and per-action levels for each connection, plus a knowledge-only mode with no execution. `execute_one_action` is marked destructive so a client can ask first, and no server-side approval step was found (17). `execute_one_action` returns third-party content. Credentials are redacted from responses and sensitive headers stripped from the request echo, and no guidance on prompt injection was found (4). The dashboard logs agent, app, action and outcome per call, including refused calls, with retention of 14 to 90 days. No export or log API was confirmed (12). security@withone.ai is given for disclosure. security.txt returned 404, the SOC 2 audit is in progress, and no bounty or published advisories were found (6).\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, 73 out of 100, up to 4.4 more on the total\n\nWhy it scored 73: Three compact tools however many apps are connected. The vendor puts the definitions at about 1.2K tokens, which we did not measure (25). `find_one_actions` takes up to 10 operations in one call and returns large documents as a digest, with sections, a table of contents or the whole document on request. `execute_one_action` returns the upstream response whole, with no size control found (14). Failures come back as tool errors the agent can read, a call outside the grant is refused with a reason, and a missing token gets a 401 with a `WWW-Authenticate` pointer. No error code catalogue for the MCP server was found (14). The docs give read-only annotations on two tools and destructive and open-world on `execute_one_action`. We could not confirm them on the live server, the local package's source sets none, and there is no idempotency key (12). `list_one_integrations` takes no parameters and `execute_one_action` needs three. Beyond the MCP server and the Node CLI, no SDK in two languages was found for this surface (8).\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, 77 out of 100, up to 3.7 more on the total\n\nWhy it scored 77: The three tools have typed inputs in the open-source local server, and the REST API has a public OpenAPI 3.1 file with 245 operations (25). llms.txt and a Markdown twin of every page (10). Tool descriptions state purpose, order of use and when not to call `execute_one_action` (17). `find_one_actions` bounds its arrays at 1 to 10, but `data`, `queryParams` and `platform` are untyped or free strings with no enums (7). The docs give request examples for `find_one_actions` and a short list of failure types, and the OpenAPI file documents 400 to 503 responses on most operations (10). The API sits under `/v1/` and registry versions are numbered, but the site's changelog has no entry after 13 July 2026 and does not record the change from four tools to three (8). We could not read the remote server's live tool schemas without an account. The remote docs use `action_id` and `connection_key` where the local source uses `actionId` and `connectionKey`.\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. Reliability, 82 out of 100, up to 3.6 more on the total\n\nWhy it scored 82: Read with the hosted lines. status.withone.ai lists API, Dashboard, Embeddable Auth and Website with daily history (20). Its feed shows no downtime in the last 90 days and no incidents posted from August to October 2026. The last recorded downtime was about 12 minutes on the API on 15 April 2026. The MCP host is not a component of its own, so 25 of 30 (25). Rate limits are published per plan at 20, 100 and 500 requests a minute, per account (15). Over the limit the API answers 429 and requests pass again as the limit refills, and a timed-out call tells the agent to check whether a write took effect. No Retry-After header and no idempotency key were found (7). The Enterprise plan lists an SLA with no published figure (5). The remote server was announced on 13 July 2026 with no beta or preview label (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## 6. Transparency \u0026 trust, 63 out of 100, up to 3.2 more on the total\n\nMade of editorial 54, provenance 72.\n\nWhy it scored 63: The editorial half. A closed hosted service under Terms of Service that name One Systems, Inc. The local MCP package is MIT, the CLI has no licence, and the knowledge base the vendor calls open source is under its own licence with anti-competition and revenue-threshold terms (15). The privacy policy has a retention table, a 72-hour breach notice and a commitment not to train AI models on customer content. The home and security pages say nothing from a call is stored, while the policy says request logs may include integration payloads for 14 to 90 days, and the DPA is not published (18). No deprecation policy or dated sunset notices were found. The terms promise 30 days' notice of price changes and material changes to the terms (3). The sub-processor list, updated 22 July 2026, names Google Cloud Platform in the United States for Customer Data and six service providers with locations (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- Domain age: withone.ai, registered 2026-01-22 (under a year) (0 of 15)\n- Terms of service: read, states 6 of the 7 things a reader expects, and has 1 clause that costs points (7.1 of 10)\n- security.txt: not found (0 of 10)\n\n## 7. Maintenance \u0026 community, 86 out of 100, up to 1.2 more on the total\n\nWhy it scored 86: `@withone/cli` 2.5.0 was published on 6 October 2026 and `@withone/mcp` 2.0.0 on 30 September (30). The CLI had 14 npm releases between 25 August and 6 October and the MCP package had nine between 12 August and 30 September (20). In the CLI repository an outside pull request was merged the day it was opened in August, and two outside issues opened on 31 August 2026 had no reply on 9 October (14). The server is in the official MCP registry as `ai.withone/mcp`, version 2.0.0, under the vendor's domain namespace (15). The CLI runs CI on Node 18, 20 and 22 on Linux and Windows. The MCP repository has tests but only a publish workflow (7).\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- Between 13 July and 30 September 2026 the remote MCP server's tools changed from four to three. The changelog entry of 13 July 2026 says the remote server has the same four tools as the local one, and the local package's 2.0.0 commit of 30 September 2026 removes `search_one_platform_actions` and `get_one_action_knowledge` for `find_one_actions`, which it calls the tool the remote server already serves. The site's changelog has no entry for the change. The local package marked it as a major version. Three points off (https://www.withone.ai/changelog, https://github.com/withoneai/mcp).\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 remote server's live `tools/list`, including input schemas and annotation hints, because reading it needs an account and we did not create one. Tool schemas were read from the open-source local package, which the docs say has the same three tools\n- unchecked: whether sign-up for the Free plan needs a card. The pricing page doesn't say and we did not sign up\n- unchecked: the dashboard's activity log, its export options and any log API\n- unchecked: the Data Processing Agreement, which is available only on request\n- The date the remote server moved from four tools to three. The evidence gives only a window from 13 July to 30 September 2026\n- Whether refused and failed calls count against the 1M requests a month, and whether a 429 carries a Retry-After header\n- Whether the monthly figure on the pricing page or the unlimited API calls on the API authentication page is current\n- The state of incorporation of One Systems, Inc., which the terms and privacy policy do not give\n- The lead named the vendor as One. The legal entity on the terms is One Systems, Inc. The rest of the lead held\n\n## Weaknesses\n\n- The remote server's tools changed from four to three by 30 September 2026, and the site's changelog, last dated 13 July 2026, has no entry for it\n- The home and security pages say nothing from a call is stored. The privacy policy says request logs may include integration payloads, kept 14 to 90 days by default\n- The SOC 2 audit is described as in progress, `/.well-known/security.txt` returned 404, and no bug bounty or published advisories were found\n- `execute_one_action` takes a free-form `data` body and returns the upstream response whole. No control on response size was found\n- The Data Processing Agreement is available only on request, and no deprecation policy 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- Call `list_one_integrations` first and read each connection's `access` field. When the policy is `actions`, run those ids directly without calling `find_one_actions`\n- Send every operation a task needs in one `find_one_actions` call, up to 10 `requests`, each a platform and a short intent with no IDs, names or message text\n- When a document comes back as a digest, call `find_one_actions` again with `load` and a `section` name. Don't guess parameters the digest left out\n- After a timeout on `execute_one_action`, check whether the write took effect before sending it again. No idempotency key is documented\n- A 403 for a call outside the grant won't succeed on retry. Ask the user to widen the grant in the dashboard or reconnect\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": 66.6,
    "assessed": "2026-10-09",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "score": 30,
        "maxGain": 8.8,
        "reason": "No x402, MPP or L402 (0). Plan prices are public with their limits, $0, $29 and $199 a month, and nothing is billed over the limit. There is no per-call price and Enterprise is on contract, so 15 of 20 (15). The Free plan includes every platform and 1M requests a month. The pricing page doesn't say whether sign-up needs a card and we did not create an account, so 15 of 20 (15). A person must sign in through a browser to approve the grant or create an API key (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 2.1 authorisation code with PKCE, scopes, one-hour access tokens, and a grant that can be narrowed or revoked from the dashboard with effect on the next call (30). Read only, Read \u0026 write, Full access and per-action levels for each connection, plus a knowledge-only mode with no execution. `execute_one_action` is marked destructive so a client can ask first, and no server-side approval step was found (17). `execute_one_action` returns third-party content. Credentials are redacted from responses and sensitive headers stripped from the request echo, and no guidance on prompt injection was found (4). The dashboard logs agent, app, action and outcome per call, including refused calls, with retention of 14 to 90 days. No export or log API was confirmed (12). security@withone.ai is given for disclosure. security.txt returned 404, the SOC 2 audit is in progress, and no bounty or published advisories were found (6).",
        "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": 73,
        "maxGain": 4.4,
        "reason": "Three compact tools however many apps are connected. The vendor puts the definitions at about 1.2K tokens, which we did not measure (25). `find_one_actions` takes up to 10 operations in one call and returns large documents as a digest, with sections, a table of contents or the whole document on request. `execute_one_action` returns the upstream response whole, with no size control found (14). Failures come back as tool errors the agent can read, a call outside the grant is refused with a reason, and a missing token gets a 401 with a `WWW-Authenticate` pointer. No error code catalogue for the MCP server was found (14). The docs give read-only annotations on two tools and destructive and open-world on `execute_one_action`. We could not confirm them on the live server, the local package's source sets none, and there is no idempotency key (12). `list_one_integrations` takes no parameters and `execute_one_action` needs three. Beyond the MCP server and the Node CLI, no SDK in two languages was found for this surface (8).",
        "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": 77,
        "maxGain": 3.7,
        "reason": "The three tools have typed inputs in the open-source local server, and the REST API has a public OpenAPI 3.1 file with 245 operations (25). llms.txt and a Markdown twin of every page (10). Tool descriptions state purpose, order of use and when not to call `execute_one_action` (17). `find_one_actions` bounds its arrays at 1 to 10, but `data`, `queryParams` and `platform` are untyped or free strings with no enums (7). The docs give request examples for `find_one_actions` and a short list of failure types, and the OpenAPI file documents 400 to 503 responses on most operations (10). The API sits under `/v1/` and registry versions are numbered, but the site's changelog has no entry after 13 July 2026 and does not record the change from four tools to three (8). We could not read the remote server's live tool schemas without an account. The remote docs use `action_id` and `connection_key` where the local source uses `actionId` and `connectionKey`.",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 82,
        "maxGain": 3.6,
        "reason": "Read with the hosted lines. status.withone.ai lists API, Dashboard, Embeddable Auth and Website with daily history (20). Its feed shows no downtime in the last 90 days and no incidents posted from August to October 2026. The last recorded downtime was about 12 minutes on the API on 15 April 2026. The MCP host is not a component of its own, so 25 of 30 (25). Rate limits are published per plan at 20, 100 and 500 requests a minute, per account (15). Over the limit the API answers 429 and requests pass again as the limit refills, and a timed-out call tells the agent to check whether a write took effect. No Retry-After header and no idempotency key were found (7). The Enterprise plan lists an SLA with no published figure (5). The remote server was announced on 13 July 2026 with no beta or preview label (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 63,
        "maxGain": 3.2,
        "reason": "The editorial half. A closed hosted service under Terms of Service that name One Systems, Inc. The local MCP package is MIT, the CLI has no licence, and the knowledge base the vendor calls open source is under its own licence with anti-competition and revenue-threshold terms (15). The privacy policy has a retention table, a 72-hour breach notice and a commitment not to train AI models on customer content. The home and security pages say nothing from a call is stored, while the policy says request logs may include integration payloads for 14 to 90 days, and the DPA is not published (18). No deprecation policy or dated sunset notices were found. The terms promise 30 days' notice of price changes and material changes to the terms (3). The sub-processor list, updated 22 July 2026, names Google Cloud Platform in the United States for Customer Data and six service providers with locations (18).",
        "blend": "editorial 54, provenance 72",
        "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": 86,
        "maxGain": 1.2,
        "reason": "`@withone/cli` 2.5.0 was published on 6 October 2026 and `@withone/mcp` 2.0.0 on 30 September (30). The CLI had 14 npm releases between 25 August and 6 October and the MCP package had nine between 12 August and 30 September (20). In the CLI repository an outside pull request was merged the day it was opened in August, and two outside issues opened on 31 August 2026 had no reply on 9 October (14). The server is in the official MCP registry as `ai.withone/mcp`, version 2.0.0, under the vendor's domain namespace (15). The CLI runs CI on Node 18, 20 and 22 on Linux and Windows. The MCP repository has tests but only a publish workflow (7).",
        "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": "Domain age",
        "value": "withone.ai, registered 2026-01-22 (under a year)",
        "points": 0,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "read, states 6 of the 7 things a reader expects, and has 1 clause that costs points",
        "points": 7.1,
        "max": 10
      },
      {
        "label": "security.txt",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "Between 13 July and 30 September 2026 the remote MCP server's tools changed from four to three. The changelog entry of 13 July 2026 says the remote server has the same four tools as the local one, and the local package's 2.0.0 commit of 30 September 2026 removes `search_one_platform_actions` and `get_one_action_knowledge` for `find_one_actions`, which it calls the tool the remote server already serves. The site's changelog has no entry for the change. The local package marked it as a major version. Three points off (https://www.withone.ai/changelog, https://github.com/withoneai/mcp)."
    ],
    "unchecked": [
      "unchecked: the remote server's live `tools/list`, including input schemas and annotation hints, because reading it needs an account and we did not create one. Tool schemas were read from the open-source local package, which the docs say has the same three tools",
      "unchecked: whether sign-up for the Free plan needs a card. The pricing page doesn't say and we did not sign up",
      "unchecked: the dashboard's activity log, its export options and any log API",
      "unchecked: the Data Processing Agreement, which is available only on request",
      "The date the remote server moved from four tools to three. The evidence gives only a window from 13 July to 30 September 2026",
      "Whether refused and failed calls count against the 1M requests a month, and whether a 429 carries a Retry-After header",
      "Whether the monthly figure on the pricing page or the unlimited API calls on the API authentication page is current",
      "The state of incorporation of One Systems, Inc., which the terms and privacy policy do not give",
      "The lead named the vendor as One. The legal entity on the terms is One Systems, Inc. The rest of the lead held"
    ],
    "weaknesses": [
      "The remote server's tools changed from four to three by 30 September 2026, and the site's changelog, last dated 13 July 2026, has no entry for it",
      "The home and security pages say nothing from a call is stored. The privacy policy says request logs may include integration payloads, kept 14 to 90 days by default",
      "The SOC 2 audit is described as in progress, `/.well-known/security.txt` returned 404, and no bug bounty or published advisories were found",
      "`execute_one_action` takes a free-form `data` body and returns the upstream response whole. No control on response size was found",
      "The Data Processing Agreement is available only on request, and no deprecation policy was found"
    ],
    "agentNotes": [
      "Call `list_one_integrations` first and read each connection's `access` field. When the policy is `actions`, run those ids directly without calling `find_one_actions`",
      "Send every operation a task needs in one `find_one_actions` call, up to 10 `requests`, each a platform and a short intent with no IDs, names or message text",
      "When a document comes back as a digest, call `find_one_actions` again with `load` and a `section` name. Don't guess parameters the digest left out",
      "After a timeout on `execute_one_action`, check whether the write took effect before sending it again. No idempotency key is documented",
      "A 403 for a call outside the grant won't succeed on retry. Ask the user to widen the grant in the dashboard or reconnect"
    ],
    "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"
  }
}