{
  "fixes": {
    "slug": "notte",
    "name": "Notte",
    "listing": "https://www.anchorterminal.com/tools/notte",
    "markdown": "# Fix list: Notte\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/notte, the October 2026 research run, assessed 8 October 2026. Grade B, 63.2 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 Notte: 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. Reliability, 58 out of 100, up to 8.4 more on the total\n\nWhy it scored 58: Graded as a hosted API. status.notte.cc on Better Stack tracks six components with 90 days of daily history (20). In the 90 days to 8 October 2026 the core API read 100 per cent and the Session API 99.98 with two outages of about 15 minutes, but the Scrape API was down on 15 days for about 6 hours in total, including 61 minutes on 3 August and 51 on 30 August, and CAPTCHA solving read 88.93 per cent, so we score one major outage (10). Concurrency is published per plan and `X-RateLimit` headers are documented, but no request rate is stated per plan (8). The docs ask for exponential backoff on 429 and describe 529 for an overloaded cluster. The SDKs do not retry, and only the payment endpoint takes an idempotency key (10). SLAs are listed for Enterprise without published terms (0). The API is version 1.9.6 (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## 2. Security \u0026 auth, 56 out of 100, up to 7.7 more on the total\n\nWhy it scored 56: A Bearer API key from the console, or OAuth on the MCP server with one scope, `email`. No key scopes or rotation guidance found (18). The browser MCP endpoint leaves out administration tools, three of its tools are read-only, and vaults keep stored credentials away from the model. No read-only key or confirmation step found (9). Pages are untrusted content. The only guidance found is one line in the Claude managed agents guide about limiting where a credential may be sent (4). Session replays, a network log endpoint and usage logs give a per-session trail (11). A valid security.txt, a disclosure policy with safe harbour and a three-business-day acknowledgement, and a SOC 2 Type 2 report on the trust centre. The security page says there is no paid bounty (14).\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. Payments \u0026 pricing, 40 out of 100, up to 7.5 more on the total\n\nWhy it scored 40: No x402, MPP or L402 on Notte's endpoints (0). Unit prices are published without login, $0.05 an hour for browser functions, $10 a GB for residential proxies, LLM tokens at the model's price, and browser sessions listed at $0 an hour (20). Free plan with $10 of credits and no card (20). A person has to sign up in the console to create a key or approve OAuth (0).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):\n\nThe published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).\n\n- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).\n\nPayment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.\n\nOpen-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol.\n\n## 4. Schema \u0026 documentation, 74 out of 100, up to 4.2 more on the total\n\nWhy it scored 74: Graded on the REST API. OpenAPI 3.1.0 at api.notte.cc/openapi.json with 77 paths and 100 operations (25). llms.txt on the site and in the docs, a Markdown twin of every docs page and a keyless documentation MCP server (10). Every operation has a summary, 362 of 1,007 schema properties carry a description, and the guides explain each product (12). 196 schemas with 46 enums and ranges such as `max_duration_minutes` up to 1,440. `chrome_args` and `extra_http_headers` are free-form (11). The errors page shows the body format and six statuses, but 98 operations document only 422 as an error (8). The spec version matches the release tags. No dated API changelog page was found, so changes are visible only through GitHub tags and the Node SDK's CHANGELOG.md (8).\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. Agent ergonomics, 75 out of 100, up to 4.1 more on the total\n\nWhy it scored 75: The browser MCP endpoint has eight compact tools, and scrape accepts selectors and a structured output schema (22). List endpoints take `page` and `page_size` up to 100, and sessions filter by `only_active` (15). Errors are a `message` and `detail` with six documented statuses and an `x-error-class` header on execution failures (11). An `idempotency-key` header is required on session payments only, stopping a session is documented as safe to repeat, and the MCP docs mark three tools read-only and five as write. We could not list the tools to confirm the annotations (12). Session start has no required fields, and Python and Node SDKs and a CLI are official (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## 6. Transparency \u0026 trust, 61 out of 100, up to 3.4 more on the total\n\nMade of editorial 36, provenance 86.\n\nWhy it scored 61: The hosted platform is closed. The core repository is public under SSPL-1.0, which is source-available and not OSI-approved, and the Node SDK is MIT (20). The privacy policy and terms answered with a bot check and were not read. The recordings page says replays are deleted after 24 hours, while an older page in the docs source gives 7 to 30 days by plan. No public DPA found (8). No deprecation policy found. The Node SDK changelog labels breaking changes and the spec marks one field deprecated (5). The trust centre page we read named no subprocessors or data locations, and other regions are an Enterprise option (3).\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: notte.cc, registered 2024-09-25 (2 years) (7 of 15)\n- Terms of service: published, but our reader couldn't read it (7 of 10)\n- Privacy policy: published, but our reader couldn't read it (7 of 10)\n\n## 7. Maintenance \u0026 community, 83 out of 100, up to 1.5 more on the total\n\nWhy it scored 83: Version 1.9.6 was tagged and published to PyPI and npm on 7 October 2026 (30). 18 tags between 10 July and 7 October 2026 (20). The repository had commits on 8 October and the vendor runs a Slack community, but GitHub refused our API request, so issue reply times are unread (10 of 25). Current official SDKs in Python and Node. The hosted MCP server was not found in the official MCP registry, so we scored the SDK line for an API (15). CI runs tests, nightly examples and documentation tests. The notte-mcp package on PyPI was last published on 13 July 2026 at 1.8.28 while the SDK moved to 1.9.6 (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## 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 terms of service and privacy policy at console.notte.cc/terms and /privacy. Both answered 429 with a Vercel security checkpoint, so the entity named, dates, data handling, SLA and governing law are unread and `provenance.terms` and `provenance.privacy` hold the linked addresses only\n- unchecked: GitHub stars and open-issue reply times. The GitHub API refused us for its rate limit, so `githubStars` is empty\n- unchecked: the MCP tool definitions and annotations. Listing tools needs a login, so the tool count and read or write hints come from the docs\n- unchecked: whether the console allows several API keys, revocation or scopes. The console needs a login\n- unchecked: the SOC 2 Type 2 report itself, and whether the trust centre lists subprocessors or a DPA behind a request form\n- The pricing page and the docs source both list browser sessions at $0 an hour. We recorded the figure as published and left it out of the unit prices, because we could not tell whether session time is free or the rate is unset\n- The docs source still holds an older limits page (Free with 2 concurrent browsers, replay retention of 7 to 30 days) that disagrees with the live pricing page and the recordings page\n- The security page says no paid bug bounty runs, while docs.notte.cc/legal/bug-bounty describes discretionary rewards of $50 to $500\n- The Node SDK changelog lists removal of vault credit card storage as a breaking change under Unreleased, while the OpenAPI document still has the vault credit card endpoints\n- The lead said MCP support was not shown. A hosted MCP server is documented at https://api.notte.cc/mcp\n- The docs open every page with a note telling AI agents to read notte.cc/skill.md and follow its setup steps. We treated it as page content and did not act on it\n\n## Weaknesses\n\n- status.notte.cc shows the Scrape API down on 15 of 90 days (about 6 hours in total) and CAPTCHA solving at 88.9 per cent availability\n- No request rate limit is stated per plan. The docs describe `X-RateLimit` headers and show a limit of 100 only as an example\n- A Vercel bot check answered 429 on the terms of service and privacy policy at console.notte.cc, so we could not read either\n- The core repository is under SSPL-1.0, which is not an OSI-approved licence. Only the Node SDK is MIT\n- No API key scopes, deprecation policy, subprocessor list or public DPA found in the reviewed documentation\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 `Authorization: Bearer $NOTTE_API_KEY` to https://api.notte.cc. A person creates the key in the console at console.notte.cc first\n- Stop every session when the task ends. Sessions close after 3 idle minutes or 15 minutes in total by default, and the Free plan caps a session at 15 minutes\n- Use https://api.notte.cc/mcp for browser work. Function and agent administration tools are only on https://api.notte.cc/mcp/full\n- Back off on 429 and on 529, which means the cluster has too many sessions. The SDKs do not retry rate limits for you\n- Download session replays within 24 hours. The recordings page says they are deleted after that\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": 63.2,
    "assessed": "2026-10-08",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 58,
        "maxGain": 8.4,
        "reason": "Graded as a hosted API. status.notte.cc on Better Stack tracks six components with 90 days of daily history (20). In the 90 days to 8 October 2026 the core API read 100 per cent and the Session API 99.98 with two outages of about 15 minutes, but the Scrape API was down on 15 days for about 6 hours in total, including 61 minutes on 3 August and 51 on 30 August, and CAPTCHA solving read 88.93 per cent, so we score one major outage (10). Concurrency is published per plan and `X-RateLimit` headers are documented, but no request rate is stated per plan (8). The docs ask for exponential backoff on 429 and describe 529 for an overloaded cluster. The SDKs do not retry, and only the payment endpoint takes an idempotency key (10). SLAs are listed for Enterprise without published terms (0). The API is version 1.9.6 (10).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 56,
        "maxGain": 7.7,
        "reason": "A Bearer API key from the console, or OAuth on the MCP server with one scope, `email`. No key scopes or rotation guidance found (18). The browser MCP endpoint leaves out administration tools, three of its tools are read-only, and vaults keep stored credentials away from the model. No read-only key or confirmation step found (9). Pages are untrusted content. The only guidance found is one line in the Claude managed agents guide about limiting where a credential may be sent (4). Session replays, a network log endpoint and usage logs give a per-session trail (11). A valid security.txt, a disclosure policy with safe harbour and a three-business-day acknowledgement, and a SOC 2 Type 2 report on the trust centre. The security page says there is no paid bounty (14).",
        "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": "payments",
        "name": "Payments \u0026 pricing",
        "score": 40,
        "maxGain": 7.5,
        "reason": "No x402, MPP or L402 on Notte's endpoints (0). Unit prices are published without login, $0.05 an hour for browser functions, $10 a GB for residential proxies, LLM tokens at the model's price, and browser sessions listed at $0 an hour (20). Free plan with $10 of credits and no card (20). A person has to sign up in the console to create a key or approve OAuth (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "score": 74,
        "maxGain": 4.2,
        "reason": "Graded on the REST API. OpenAPI 3.1.0 at api.notte.cc/openapi.json with 77 paths and 100 operations (25). llms.txt on the site and in the docs, a Markdown twin of every docs page and a keyless documentation MCP server (10). Every operation has a summary, 362 of 1,007 schema properties carry a description, and the guides explain each product (12). 196 schemas with 46 enums and ranges such as `max_duration_minutes` up to 1,440. `chrome_args` and `extra_http_headers` are free-form (11). The errors page shows the body format and six statuses, but 98 operations document only 422 as an error (8). The spec version matches the release tags. No dated API changelog page was found, so changes are visible only through GitHub tags and the Node SDK's CHANGELOG.md (8).",
        "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": "ergonomics",
        "name": "Agent ergonomics",
        "score": 75,
        "maxGain": 4.1,
        "reason": "The browser MCP endpoint has eight compact tools, and scrape accepts selectors and a structured output schema (22). List endpoints take `page` and `page_size` up to 100, and sessions filter by `only_active` (15). Errors are a `message` and `detail` with six documented statuses and an `x-error-class` header on execution failures (11). An `idempotency-key` header is required on session payments only, stopping a session is documented as safe to repeat, and the MCP docs mark three tools read-only and five as write. We could not list the tools to confirm the annotations (12). Session start has no required fields, and Python and Node SDKs and a CLI are official (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": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 61,
        "maxGain": 3.4,
        "reason": "The hosted platform is closed. The core repository is public under SSPL-1.0, which is source-available and not OSI-approved, and the Node SDK is MIT (20). The privacy policy and terms answered with a bot check and were not read. The recordings page says replays are deleted after 24 hours, while an older page in the docs source gives 7 to 30 days by plan. No public DPA found (8). No deprecation policy found. The Node SDK changelog labels breaking changes and the spec marks one field deprecated (5). The trust centre page we read named no subprocessors or data locations, and other regions are an Enterprise option (3).",
        "blend": "editorial 36, provenance 86",
        "checklist": [
          "- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).",
          "The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-transparency"
      },
      {
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "score": 83,
        "maxGain": 1.5,
        "reason": "Version 1.9.6 was tagged and published to PyPI and npm on 7 October 2026 (30). 18 tags between 10 July and 7 October 2026 (20). The repository had commits on 8 October and the vendor runs a Slack community, but GitHub refused our API request, so issue reply times are unread (10 of 25). Current official SDKs in Python and Node. The hosted MCP server was not found in the official MCP registry, so we scored the SDK line for an API (15). CI runs tests, nightly examples and documentation tests. The notte-mcp package on PyPI was last published on 13 July 2026 at 1.8.28 while the SDK moved to 1.9.6 (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": "Domain age",
        "value": "notte.cc, registered 2024-09-25 (2 years)",
        "points": 7,
        "max": 15
      },
      {
        "label": "Terms of service",
        "value": "published, but our reader couldn't read it",
        "points": 7,
        "max": 10
      },
      {
        "label": "Privacy policy",
        "value": "published, but our reader couldn't read it",
        "points": 7,
        "max": 10
      }
    ],
    "unchecked": [
      "unchecked: the terms of service and privacy policy at console.notte.cc/terms and /privacy. Both answered 429 with a Vercel security checkpoint, so the entity named, dates, data handling, SLA and governing law are unread and `provenance.terms` and `provenance.privacy` hold the linked addresses only",
      "unchecked: GitHub stars and open-issue reply times. The GitHub API refused us for its rate limit, so `githubStars` is empty",
      "unchecked: the MCP tool definitions and annotations. Listing tools needs a login, so the tool count and read or write hints come from the docs",
      "unchecked: whether the console allows several API keys, revocation or scopes. The console needs a login",
      "unchecked: the SOC 2 Type 2 report itself, and whether the trust centre lists subprocessors or a DPA behind a request form",
      "The pricing page and the docs source both list browser sessions at $0 an hour. We recorded the figure as published and left it out of the unit prices, because we could not tell whether session time is free or the rate is unset",
      "The docs source still holds an older limits page (Free with 2 concurrent browsers, replay retention of 7 to 30 days) that disagrees with the live pricing page and the recordings page",
      "The security page says no paid bug bounty runs, while docs.notte.cc/legal/bug-bounty describes discretionary rewards of $50 to $500",
      "The Node SDK changelog lists removal of vault credit card storage as a breaking change under Unreleased, while the OpenAPI document still has the vault credit card endpoints",
      "The lead said MCP support was not shown. A hosted MCP server is documented at https://api.notte.cc/mcp",
      "The docs open every page with a note telling AI agents to read notte.cc/skill.md and follow its setup steps. We treated it as page content and did not act on it"
    ],
    "weaknesses": [
      "status.notte.cc shows the Scrape API down on 15 of 90 days (about 6 hours in total) and CAPTCHA solving at 88.9 per cent availability",
      "No request rate limit is stated per plan. The docs describe `X-RateLimit` headers and show a limit of 100 only as an example",
      "A Vercel bot check answered 429 on the terms of service and privacy policy at console.notte.cc, so we could not read either",
      "The core repository is under SSPL-1.0, which is not an OSI-approved licence. Only the Node SDK is MIT",
      "No API key scopes, deprecation policy, subprocessor list or public DPA found in the reviewed documentation"
    ],
    "agentNotes": [
      "Send `Authorization: Bearer $NOTTE_API_KEY` to https://api.notte.cc. A person creates the key in the console at console.notte.cc first",
      "Stop every session when the task ends. Sessions close after 3 idle minutes or 15 minutes in total by default, and the Free plan caps a session at 15 minutes",
      "Use https://api.notte.cc/mcp for browser work. Function and agent administration tools are only on https://api.notte.cc/mcp/full",
      "Back off on 429 and on 529, which means the cluster has too many sessions. The SDKs do not retry rate limits for you",
      "Download session replays within 24 hours. The recordings page says they are deleted after that"
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-08",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}