PixelCheck (xcodethink/pixelcheck) is an MCP server listed on the M8ven Trust Index. It scores 74 out of 100, grade C. It declares 14 tools. No publisher has claimed this listing.

Emerging

74/100

PixelCheck

Item: PixelCheck
Rating: 74
Author: M8ven

An MCP server that gives AI agents real browser capabilities including screenshotting, action execution, data extraction, and multi-persona auditing for frontend validation.

→ xcodethink/pixelcheck · listed on glama

Emerging. No concerning findings. Grades remain capped until the project builds reputation through adoption. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

xcodethink

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

🚨

Secret credentials may flow to a network call

1 flow detected: TELEGRAM_BOT_TOKEN. We can’t prove the destination matches the brand the credential belongs to.

🔐

You'll be asked for 3 credentials: ANTHROPIC_API_KEY, STRIPE_TEST_PUBLISHABLE_KEY, TELEGRAM_BOT_TOKEN

These are read from process.env at runtime. Make sure you trust where they’ll be sent.

// tools this server exposes14 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

act

Execute a sequence of actions on a URL: goto / click / fill / press / wait / wait_for / scroll / screenshot, plus AI steps `act` (Stagehand natural language) and `note` (one vision call). Returns per-step status, final DOM summary, console errors, and a final screenshot. Engine auto-selects: Stageha…

audit_url

Run a UX audit against a URL using one persona. Returns the audit summary + report path.

calibrate_critic

Run the critic calibration gate against labeled screenshot fixtures. Returns pass/fail + metrics.

compare

A/B page comparison primitive. Each side is `{url}` or a pre-captured `{capture}`. Default mode `double_blind` judges each side independently with the same rubric (parallel) then runs ONE synthesis vision call seeing both screenshots — 3 vision calls total, free of anchoring bias (commercial UX-revi…

diagnose

Holistic page-health diagnosis (ADR-034 / Phase 0 entrypoint). Captures a URL with eager visual scoring, reads every diagnostics dimension (performance / network / popups / cookies / storage / visual), and produces a commercial-grade structured report: per-finding severity + dimension + confidence +…

doctor

explore_url

Send the autonomous agent to explore a URL with a free-form goal. Faster than audit_url; no scenario file required.

extract

Schema-bound structured extraction from a URL. Caller hands us a JSON Schema describing the desired payload shape; the tool runs Stagehand's extract() under the hood and returns matching `data` plus DOM summary, console errors, and a screenshot. Single LLM call per invocation. Single engine: Stageha…

get_last_report

Read the most recent audit's summary JSON from the reports history DB.

judge

Single-page rubric-driven critic. Captures a URL (or accepts a pre-captured snapshot) and runs one vision call against the chosen rubric(s). Built-in rubrics: 'aesthetic' (8 criteria — visual hierarchy, typography, alignment, contrast, spacing, polish, density, brand cohesion) and 'dark_pattern' (12…

list_capabilities

Self-describe the MCP server. Returns every shipped tool with its kind, input schema, result schema title, cacheability, static cost-estimate band, side-effects, and dependency declarations; plus the public env-var table and live state of the result cache. Pure introspection — no LLM, no browser, no…

list_personas

List all personas available in the project's personas/ directory.

list_scenarios

List all scenarios available in the project's scenarios/ directory.

see

Look at a URL once and return DOM summary + screenshot + console errors + an optional vision note. Lightweight primitive: 0 LLM cost when goal is omitted, ~1 vision call when set. Faster than audit_url / explore_url for one-shot inspection.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configADMIN_COOKIE

🔐 secretANTHROPIC_API_KEY"env": { "": "sk-ant-..." }

configAUDIT_ACTS_DIR

configAUDIT_COMPARES_DIR

configAUDIT_COST_GUARD_DISABLEDunset 1 / true to bypass entirely (CI / tests)

configAUDIT_COST_LEDGER_PATHPer-day — UTC-day total persisted across processes in a JSON ledger (default ~/.pixelcheck/cost-ledger.json, override via ).

configAUDIT_COST_MODE

configAUDIT_DEBUG_LOG

configAUDIT_DIAGNOSE_DIR

configAUDIT_EXTRACTS_DIR

configAUDIT_HOME

configAUDIT_JUDGES_DIR

configAUDIT_MEMORY_DISABLED

configAUDIT_MEMORY_PATH

configAUDIT_PLAN_CACHE_DISABLED

configAUDIT_PLAN_CACHE_PATH

configAUDIT_REDACT_INPUTS

configAUDIT_RESULT_CACHE_DISABLEDunset 1 / true to bypass entirely (read = miss, write = no-op)

configAUDIT_RESULT_CACHE_PATH~/.pixelcheck/result-cache.db SQLite path; isolate per environment

configAUDIT_SEES_DIR

configHTTPS_PROXY

configLOG_FILE/path/to.log unset Additionally tee logs to a file

configLOG_LEVELtrace, debug, info, warn, error, fatal, silent info Minimum log level

configLOG_PRETTY1, true, 0, false, auto auto Force pretty-print or JSON; auto decides by TTY

configMAIL_TM_BASE

configNO_PROXY

configOLLAMA_BASE_URL

configOLLAMA_CHAT_MODEL

configOLLAMA_MODEL

configPIXELCHECK_DEBUG_LOG

configPIXELCHECK_HOME

configPIXELCHECK_LLM_FALLBACK

configPIXELCHECK_LLM_PROVIDER

configPIXELCHECK_LLM_TIMEOUT_MS

configPIXELCHECK_MAX_RETRIES

configPIXELCHECK_STAGEHAND_INIT_TIMEOUT_MS

configPIXELCHECK_UNIT_DEADLINE_MS

configPIXELCHECK_VERBOSITY

configPLAYWRIGHT_BROWSERS_PATH

configSLACK_WEBHOOK

configSTRIPE_TEST_CARD_CVC

configSTRIPE_TEST_CARD_EXP

configSTRIPE_TEST_CARD_NUMBER

🔐 secretSTRIPE_TEST_PUBLISHABLE_KEY

🔐 secretTELEGRAM_BOT_TOKEN

configTELEGRAM_CHAT_ID

confighttps_proxy

configno_proxy

// quality suggestions

Dependencies

37 dependencies, 3 flagged: playwright, playwright-core, @playwright/test

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

14/14 tools missing one or more hints — act (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); audit_url (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); calibrate_critic (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +11 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Shell command execution

2 child_process/subprocess calls in production code — runs shell commands (src/core/browser-install.ts:326, src/core/browser-install.ts:545)

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

No arbitrary install scripts

Has postinstall/preinstall script — runs arbitrary code on npm install

Remove postinstall/preinstall hooks unless they’re essential.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 4 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Score](https://m8ven.ai/badge/mcp/xcodethink/pixelcheck)](https://m8ven.ai/mcp/xcodethink/pixelcheck)

Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.

commit: 2a35c25ad4b1bdbd933cec1d1e71c47abe9c1b96

code hash: 43723580b85b94b557c65cfb4e7321d3fe55238e8057d0fa270216c5d53e459e

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client