Playwright MCP by Microsoft

# Fix list: Playwright MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/playwright-mcp, the October 2026 research run, assessed 1 October 2026. Grade B, 67.6 out of 100.

This 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.

For a coding agent working on Playwright 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.

## 1. Reliability, 57 out of 100, up to 8.6 more on the total

Why it scored 57: Scored as a local stdio package (it also serves HTTP with `--port`). Official npm package @playwright/mcp with Node 18 or later stated. It pins alpha builds of Playwright (1.64.0-alpha) as dependencies (20). CI runs lint, tests on Ubuntu, macOS and Windows and a Docker test on every push and pull request. Most MCP tests live in the main Playwright repository. We didn't see the run status, so 20 of 25. Issues have been redirected to microsoft/playwright since 29 June 2026, and GitHub's robots rules blocked our search there, so we couldn't count open crash reports (12). Versions run 0.0.x with release notes on GitHub but no semver meaning (5). Not 1.0 and not declared stable (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability):

Hosted APIs, MCP servers, models and platforms.

- 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own).
- 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.
- 15, rate limits documented with numbers.
- 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved.
- 10, an SLA published for any paid tier.
- 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.
- 25, a public CI and test suite, passing on the default branch.
- 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered).
- 15, semver discipline and breaking changes called out in a changelog.
- 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.

## 2. Security & auth, 57 out of 100, up to 7.5 more on the total

Why it scored 57: No credentials to leak and nothing to scope, so the middle band (20). The HTTP transport binds localhost by default and checks the Host header against DNS rebinding, but has no authentication. File access is limited to workspace roots unless `--allow-unrestricted-file-access`, and `--secrets` masks values in responses. `--isolated` is off by default, the allowed and blocked origin lists say they aren't a security boundary, and `browser_run_code_unsafe`, described in its own text as RCE-equivalent in the server process, sits in the core set that can't be switched off (10). Page content is untrusted and we found no prompt-injection guidance (0). `--save-session`, traces, video and generated Playwright code for each action give the operator a record (12). Microsoft's MSRC reporting policy in SECURITY.md, and no advisories published for this repository (15).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-security):

- 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.
- 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions.
- 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.
- 0 to 15, audit logs or per-call visibility for the operator.
- 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.

## 3. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Free, self-hosted, nothing to buy, so 20 + 20 + 20. No payment protocol (0).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments):

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.
- 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.
- 20, a free tier or trial that doesn't need a card.
- 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.

## 4. Schema & documentation, 70 out of 100, up to 4.9 more on the total

Why it scored 70: Every tool's input is a Zod schema turned into JSON Schema (25). The README's tool list is generated from the source. No llms.txt (5). Descriptions are mostly one line, "Perform click on a web page" or "Returns all console messages". `browser_find` and `browser_snapshot` explain when they're cheaper, and the README says when to prefer the CLI over MCP (10). Enums for mouse buttons, modifiers and console levels, `depth` on snapshots, and a free-form MIME map on `browser_drop` (13). Few examples beyond `browser_run_code_unsafe` and `browser_find`, and no documented error list (7). GitHub release notes for each 0.0.x version (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema):

APIs and MCP servers.

- 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool).
- 10, llms.txt or Markdown docs served for agents.
- 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.
- 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs.
- 0 to 15, examples and documented error responses.
- 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.

## 5. Agent ergonomics, 84 out of 100, up to 2.6 more on the total

Why it scored 84: 72 tools in the README across ten groups. Only core and tabs load by default, 25 tools (15). `--caps` adds network, storage, devtools, vision, PDF, testing and config groups only when asked, and `--snapshot-mode none` and `--image-responses omit` trim each response (plus 10). `browser_find` searches the snapshot instead of returning it, snapshots take `depth`, and most read tools can write to a file instead of the response (17). Modal-state errors name the tool that clears them (14). Every tool carries `readOnlyHint`, `destructiveHint` and `openWorldHint`, 29 marked read-only. Every other tool is marked destructive, hover included, which blunts the signal (18). Few required parameters and defaults that work. npm and Docker only (10).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics):

- 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).
- 20, pagination, filtering and output-size controls.
- 20, actionable, documented error responses, codes and messages an agent can recover from.
- 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations.
- 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.

## 6. Transparency & trust, 72 out of 100, up to 2.5 more on the total

Made of editorial 75, provenance 68.

Why it scored 72: Apache-2.0 (30). Local software. There's no written data statement, but we found no telemetry or remote calls beyond the pages it's asked to open in the MCP code (20). No deprecation policy, and 0.0.x versioning gives no notice of tool renames (5). No telemetry in the source we read (20).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency):

- 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.
- 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors).
- 0 to 20, a deprecation policy or notices with dates.
- 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.

Provenance checks not met in full (half of this category, computed from checked facts):

- Domain age: playwright.dev, registered 2019-09-18 (7 years) (11 of 15)
- Status page: not found (0 of 10)
- security.txt: not found (0 of 10)

## 7. Maintenance & community, 84 out of 100, up to 1.4 more on the total

Why it scored 84: v0.0.83 on 2026-09-28 (30). Six releases since 3 July, v0.0.78 to v0.0.83 (20). Issues moved to microsoft/playwright on 29 June 2026 with a pinned notice. We couldn't read the MCP issues there, and Dependabot pull requests here merge within days (12). Published to the official MCP registry as io.github.microsoft/playwright-mcp by an OIDC workflow on each release. The registry API timed out on our reads, so this rests on the workflow and server.json at 0.0.83 (15). Pinned actions and Dependabot, but the package tracks alpha Playwright builds (7).

The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance):

- 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.
- 20, at least three releases or dated changelog entries in the last 90 days.
- 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.
- 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models).
- 10, package health, current dependencies and CI.

Models are read for deprecation notice periods and model churn rather than release counts.

## What we couldn't check

What 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.

- unchecked: open MCP crash or regression reports in microsoft/playwright, since GitHub's robots rules blocked our issue search there
- unchecked: the registry entry itself, because registry.modelcontextprotocol.io timed out twice. The publish workflow and server.json show 0.0.83
- unchecked: whether the default branch's CI runs currently pass

## Weaknesses

- `browser_run_code_unsafe` runs arbitrary JavaScript in the server process and can't be switched off
- No authentication on the HTTP transport, and `--isolated` is off by default
- Still 0.0.x after 83 releases, with alpha Playwright builds as dependencies
- One-line tool descriptions and no error list
- Issues moved to the main Playwright tracker, where MCP reports mix with everything else

## What costs an agent a turn today

The notes we give agents before they call it. Each one is a workaround an agent shouldn't need.

- Call `browser_find` before `browser_snapshot` when you only need one element's ref
- Pass `depth` or a `target` to `browser_snapshot` on large pages
- Run with `--isolated` for untrusted sites. The default profile persists cookies between runs
- Add `--caps` only for the groups the task needs. Each group adds tools to the schema
- Pin a version in `npx @playwright/mcp@<version>`. 0.0.x releases can rename tools

## What the review panel asked for

- Stable tool names
- Flag to drop run_code_unsafe
- removable code tool
- HTTP transport auth

## When it's done

Send 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.