{
  "fixes": {
    "slug": "chrome-devtools-mcp",
    "name": "Chrome DevTools MCP",
    "listing": "https://www.anchorterminal.com/tools/chrome-devtools-mcp",
    "markdown": "# Fix list: Chrome DevTools MCP\n\nFrom Anchor Terminal's listing at https://www.anchorterminal.com/tools/chrome-devtools-mcp, the October 2026 research run, assessed 1 October 2026. Grade BB, 77.1 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 Chrome DevTools MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published.\n\n## 1. Security \u0026 auth, 63 out of 100, up to 6.5 more on the total\n\nWhy it scored 63: No credentials to leak and nothing to scope, so the middle band (20). `--javascript-evaluation false` disables script tools and `javascript:`, `data:` and `vbscript:` URLs, `--allowed-url-pattern` and `--blocked-url-pattern` restrict the browser, MCP roots confine file access, and `--isolated` uses a throwaway profile. No confirmation step for writes, and `--isolated` and header redaction are both off by default (14). SECURITY.md says page content comes back as-is and tells users to prefer trusted content or have the client guard against prompt injection (8). A `--log-file` debug log only, no per-call audit (3). Reports go through Google's open-source vulnerability reward programme, and two moderate advisories were published in public in June 2026 (18).\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## 2. Payments \u0026 pricing, 60 out of 100, up to 5 more on the total\n\nWhy it scored 60: Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (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## 3. Reliability, 83 out of 100, up to 3.4 more on the total\n\nWhy it scored 83: Scored as a local stdio package. Official npm package, with Node ^20.19, ^22.12 or 23 and later in `engines` and Chrome stable and Chrome for Testing named as supported (20). Tests run on every push and pull request across Ubuntu, Windows and macOS on Node 22, 24 and 26, plus a memory-leak workflow. We didn't see the run status, so 20 of 25. 77 open issues, most carrying triage labels (confirmed, p2, collecting-feedback). Open bugs include `performance_stop_trace` throwing on traces over about 512 MB (#2701) and screenshots capturing the wrong region after scrolling (#2684) (18). release-please writes the changelog from conventional commits, but 1.8.0 on 25 August made `pageId` required by default and filed it under `Features` in a minor release (10). 1.0.0 shipped on 18 May 2026 (15).\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## 4. Agent ergonomics, 83 out of 100, up to 2.8 more on the total\n\nWhy it scored 83: 59 tools in the full reference across 11 categories. About 30 load by default, since extensions, PWA, third-party, WebMCP, vision, screencast and 13 of the 14 memory tools sit behind flags (15). Category flags turn groups off, and `--slim` cuts the list to three tools (navigate, evaluate, screenshot) (plus 10). `list_network_requests` and `list_console_messages` page and filter by resource type, and large outputs can go to a file path instead of inline (20). Errors come back as tool text, and dialogue boxes that block a tool are reported, but we found no documented error codes (14). Every tool sets `readOnlyHint` (28 true, 39 false in the source), with no `destructiveHint` (14). Few required parameters, but `pageId` has been required on page tools by default since 1.8.0. npm only (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):\n\n- 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries).\n- 20, pagination, filtering and output-size controls.\n- 20, actionable, documented error responses, codes and messages an agent can recover from.\n- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.\n- 15, sensible defaults, few required parameters, and official SDKs in at least two languages.\n\nModels are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs.\n\n## 5. Schema \u0026 documentation, 87 out of 100, up to 2.1 more on the total\n\nWhy it scored 87: Every tool has a Zod input schema with types, required fields and enums (25). Generated Markdown tool references in the repository and an Agent skills folder, but no llms.txt (7). Descriptions say what each tool does and often when, for example `evaluate_script` tells the model to pass `waitForStableDom: false` when it only reads, with sample functions. Few say when not to use a tool (16). Enums such as `format` (`function` or `script`), numeric page ids and file-path options (13). Inline examples in descriptions and a troubleshooting guide covering common errors, but no error catalogue (11). CHANGELOG.md for every release since 0.x (15).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):\n\nAPIs and MCP servers.\n\n- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.\n\nModels are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference.\n\n## 6. Transparency \u0026 trust, 82 out of 100, up to 1.6 more on the total\n\nMade of editorial 76, provenance 88.\n\nWhy it scored 82: Apache-2.0 (30). The README says usage statistics go to Google under its privacy policy and that performance tools send trace URLs to the CrUX API. No retention figures for either (20). No deprecation policy. The README commits to supporting the latest Extended Stable Chrome (6). Usage statistics are on by default, disclosed at the top of the README, with `--no-usage-statistics`, an environment variable and automatic opt-out under CI. CrUX lookups switch off with `--no-performance-crux` (20).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):\n\n- 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms.\n- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).\n- 0 to 20, a deprecation policy or notices with dates.\n- 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted).\n\nThe other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two.\n\nProvenance checks not met in full (half of this category, computed from checked facts):\n\n- Status page: not found (0 of 10)\n\n## 7. Maintenance \u0026 community, 93 out of 100, up to 0.6 more on the total\n\nWhy it scored 93: 1.10.1 on 2026-09-23 (30). Seven releases since 3 July, 1.5.0 to 1.10.1 (20). Open issues carry triage labels within days, though the ten newest showed no maintainer comments in the list view (18). Listed in the official MCP registry as io.github.ChromeDevTools/chrome-devtools-mcp, published by a workflow on each tag (15). CI matrix across three systems and three Node versions, GitHub Actions pinned by commit hash (10).\n\nThe checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):\n\n- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.\n\nModels are read for deprecation notice periods and model churn rather than release counts.\n\n## Deductions\n\nEach comes off the total. A fixed and documented problem counts for less at the next check.\n\n- -1: two moderate advisories published by the maintainers, GHSA-3pvj-jv98-qhjq on 2026-06-15 (daemon.pid written through symlinks in the /tmp fallback directory) and GHSA-8qf9-62x2-82pp on 2026-06-16 (path validation not canonicalising symlinks before enforcing roots). Fixed and disclosed in public, so a small deduction (https://github.com/ChromeDevTools/chrome-devtools-mcp/security/advisories).\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: whether the default branch's test runs currently pass\n- unchecked: the exact default tool count. We counted about 30 from the category defaults and flag conditions in the source, not from a running tools/list\n- The registry search page we read showed versions up to 0.25.0 and was cut at 30 entries, so we didn't confirm the 1.10.1 entry there, though server.json and the publish workflow are both at 1.10.1\n\n## Weaknesses\n\n- Usage statistics go to Google by default until you pass `--no-usage-statistics`\n- `--isolated` and network header redaction are off by default, so the agent sees a persistent profile and raw headers\n- 1.8.0 made `pageId` required on page tools in a minor release, filed under `Features`\n- SECURITY.md treats prompt injection from page content as the client's problem\n- 77 open issues, including traces over about 512 MB failing to stop\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- Pass `pageId` on every page tool. Call `list_pages` first to get it\n- Start with `--slim` for plain browsing, or turn off categories you don't need\n- Run with `--isolated` for untrusted sites. The default profile persists between runs\n- Use `filePath` on large outputs such as traces and snapshots to keep them out of context\n- Add `--no-usage-statistics` if the operator hasn't agreed to Google telemetry\n\n## What the review panel asked for\n\n- telemetry off by default (2 reviews)\n- a major version for breaking changes\n- a breaking-changes heading in the changelog\n- Leaner default tool set\n- Token counts per tool\n- Document the default tool count\n- Add destructiveHint\n- fix #2684\n- llms.txt\n- Document error codes\n- Pin the install\n- Isolated profile by default\n- Telemetry opt-in\n- `--isolated` on by default\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": "BB",
    "score": 77.1,
    "assessed": "2026-10-01",
    "run": "October 2026 research run",
    "categories": [
      {
        "key": "security",
        "name": "Security \u0026 auth",
        "score": 63,
        "maxGain": 6.5,
        "reason": "No credentials to leak and nothing to scope, so the middle band (20). `--javascript-evaluation false` disables script tools and `javascript:`, `data:` and `vbscript:` URLs, `--allowed-url-pattern` and `--blocked-url-pattern` restrict the browser, MCP roots confine file access, and `--isolated` uses a throwaway profile. No confirmation step for writes, and `--isolated` and header redaction are both off by default (14). SECURITY.md says page content comes back as-is and tells users to prefer trusted content or have the client guard against prompt injection (8). A `--log-file` debug log only, no per-call audit (3). Reports go through Google's open-source vulnerability reward programme, and two moderate advisories were published in public in June 2026 (18).",
        "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": 60,
        "maxGain": 5,
        "reason": "Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0).",
        "checklist": [
          "The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/).",
          "- 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which.\n- 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for \"contact sales\" or prices behind a login.\n- 20, a free tier or trial that doesn't need a card.\n- 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API).",
          "Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied.",
          "Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-payments"
      },
      {
        "key": "reliability",
        "name": "Reliability",
        "score": 83,
        "maxGain": 3.4,
        "reason": "Scored as a local stdio package. Official npm package, with Node ^20.19, ^22.12 or 23 and later in `engines` and Chrome stable and Chrome for Testing named as supported (20). Tests run on every push and pull request across Ubuntu, Windows and macOS on Node 22, 24 and 26, plus a memory-leak workflow. We didn't see the run status, so 20 of 25. 77 open issues, most carrying triage labels (confirmed, p2, collecting-feedback). Open bugs include `performance_stop_trace` throwing on traces over about 512 MB (#2701) and screenshots capturing the wrong region after scrolling (#2684) (18). release-please writes the changelog from conventional commits, but 1.8.0 on 25 August made `pageId` required by default and filed it under `Features` in a minor release (10). 1.0.0 shipped on 18 May 2026 (15).",
        "checklist": [
          "Hosted APIs, MCP servers, models and platforms.",
          "- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).\n- 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so.\n- 15, rate limits documented with numbers.\n- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.\n- 10, an SLA published for any paid tier.\n- 10, the surface agents use is generally available, not beta or preview.",
          "Local packages, SDKs, frameworks and stdio MCP servers.",
          "- 20, installs from an official package with supported runtimes stated.\n- 25, a public CI and test suite, passing on the default branch.\n- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).\n- 15, semver discipline and breaking changes called out in a changelog.\n- 15, version 1.0 or later, or declared stable.",
          "Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-reliability"
      },
      {
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "score": 83,
        "maxGain": 2.8,
        "reason": "59 tools in the full reference across 11 categories. About 30 load by default, since extensions, PWA, third-party, WebMCP, vision, screencast and 13 of the 14 memory tools sit behind flags (15). Category flags turn groups off, and `--slim` cuts the list to three tools (navigate, evaluate, screenshot) (plus 10). `list_network_requests` and `list_console_messages` page and filter by resource type, and large outputs can go to a file path instead of inline (20). Errors come back as tool text, and dialogue boxes that block a tool are reported, but we found no documented error codes (14). Every tool sets `readOnlyHint` (28 true, 39 false in the source), with no `destructiveHint` (14). Few required parameters, but `pageId` has been required on page tools by default since 1.8.0. npm only (10).",
        "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": 87,
        "maxGain": 2.1,
        "reason": "Every tool has a Zod input schema with types, required fields and enums (25). Generated Markdown tool references in the repository and an Agent skills folder, but no llms.txt (7). Descriptions say what each tool does and often when, for example `evaluate_script` tells the model to pass `waitForStableDom: false` when it only reads, with sample functions. Few say when not to use a tool (16). Enums such as `format` (`function` or `script`), numeric page ids and file-path options (13). Inline examples in descriptions and a troubleshooting guide covering common errors, but no error catalogue (11). CHANGELOG.md for every release since 0.x (15).",
        "checklist": [
          "APIs and MCP servers.",
          "- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).\n- 10, llms.txt or Markdown docs served for agents.\n- 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference.\n- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.\n- 0 to 15, examples and documented error responses.\n- 15, versioning and a public changelog.",
          "Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-schema"
      },
      {
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "score": 82,
        "maxGain": 1.6,
        "reason": "Apache-2.0 (30). The README says usage statistics go to Google under its privacy policy and that performance tools send trace URLs to the CrUX API. No retention figures for either (20). No deprecation policy. The README commits to supporting the latest Extended Stable Chrome (6). Usage statistics are on by default, disclosed at the top of the README, with `--no-usage-statistics`, an environment variable and automatic opt-out under CI. CrUX lookups switch off with `--no-performance-crux` (20).",
        "blend": "editorial 76, 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": 93,
        "maxGain": 0.6,
        "reason": "1.10.1 on 2026-09-23 (30). Seven releases since 3 July, 1.5.0 to 1.10.1 (20). Open issues carry triage labels within days, though the ten newest showed no maintainer comments in the list view (18). Listed in the official MCP registry as io.github.ChromeDevTools/chrome-devtools-mcp, published by a workflow on each tag (15). CI matrix across three systems and three Node versions, GitHub Actions pinned by commit hash (10).",
        "checklist": [
          "- 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older.\n- 20, at least three releases or dated changelog entries in the last 90 days.\n- 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15.\n- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).\n- 10, package health, current dependencies and CI.",
          "Models are read for deprecation notice periods and model churn rather than release counts."
        ],
        "checklistUrl": "https://www.anchorterminal.com/benchmark/#checklist-maintenance"
      }
    ],
    "provenance": [
      {
        "label": "Status page",
        "value": "not found",
        "points": 0,
        "max": 10
      }
    ],
    "deductions": [
      "-1: two moderate advisories published by the maintainers, GHSA-3pvj-jv98-qhjq on 2026-06-15 (daemon.pid written through symlinks in the /tmp fallback directory) and GHSA-8qf9-62x2-82pp on 2026-06-16 (path validation not canonicalising symlinks before enforcing roots). Fixed and disclosed in public, so a small deduction (https://github.com/ChromeDevTools/chrome-devtools-mcp/security/advisories)."
    ],
    "unchecked": [
      "unchecked: whether the default branch's test runs currently pass",
      "unchecked: the exact default tool count. We counted about 30 from the category defaults and flag conditions in the source, not from a running tools/list",
      "The registry search page we read showed versions up to 0.25.0 and was cut at 30 entries, so we didn't confirm the 1.10.1 entry there, though server.json and the publish workflow are both at 1.10.1"
    ],
    "weaknesses": [
      "Usage statistics go to Google by default until you pass `--no-usage-statistics`",
      "`--isolated` and network header redaction are off by default, so the agent sees a persistent profile and raw headers",
      "1.8.0 made `pageId` required on page tools in a minor release, filed under `Features`",
      "SECURITY.md treats prompt injection from page content as the client's problem",
      "77 open issues, including traces over about 512 MB failing to stop"
    ],
    "agentNotes": [
      "Pass `pageId` on every page tool. Call `list_pages` first to get it",
      "Start with `--slim` for plain browsing, or turn off categories you don't need",
      "Run with `--isolated` for untrusted sites. The default profile persists between runs",
      "Use `filePath` on large outputs such as traces and snapshots to keep them out of context",
      "Add `--no-usage-statistics` if the operator hasn't agreed to Google telemetry"
    ],
    "requests": [
      {
        "text": "telemetry off by default",
        "reviews": 2
      },
      {
        "text": "a major version for breaking changes",
        "reviews": 1
      },
      {
        "text": "a breaking-changes heading in the changelog",
        "reviews": 1
      },
      {
        "text": "Leaner default tool set",
        "reviews": 1
      },
      {
        "text": "Token counts per tool",
        "reviews": 1
      },
      {
        "text": "Document the default tool count",
        "reviews": 1
      },
      {
        "text": "Add destructiveHint",
        "reviews": 1
      },
      {
        "text": "fix #2684",
        "reviews": 1
      },
      {
        "text": "llms.txt",
        "reviews": 1
      },
      {
        "text": "Document error codes",
        "reviews": 1
      },
      {
        "text": "Pin the install",
        "reviews": 1
      },
      {
        "text": "Isolated profile by default",
        "reviews": 1
      },
      {
        "text": "Telemetry opt-in",
        "reviews": 1
      },
      {
        "text": "`--isolated` on by default",
        "reviews": 1
      }
    ],
    "recheck": "https://www.anchorterminal.com/builders/#disputes"
  },
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-05",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  }
}