Pixelcheck vs MCP Server Browser
A side-by-side look at the Pixelcheck and MCP Server Browser MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Pixelcheck for browser automation work as a local process; choose MCP Server Browser for browser automation as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Pixelcheck when
- You need dedicated capabilities in the Browser Automation domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
ANTHROPIC_API_KEY. - You want tools like
audit_url, explore_url, see.
Choose MCP Server Browser when
- You need dedicated capabilities in the Browser Automation domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
browser_click, browser_close, browser_close_tab.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Browser Automation | Browser Automation |
| Quality signal | 57/100 · Good | 67/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | No auth required |
| Pricing | Not declared | Free |
| Required env vars | ANTHROPIC_API_KEY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 6 | 39,368 |
| Directory activity | 0 views 0 installs 0 upvotes | 6 views 0 installs 0 upvotes |
| Tools | 12 | 23 |
| Full listing | View Pixelcheck | View MCP Server Browser |
Tools & capabilities
Pixelcheck tools 12
audit_urlYou want the full audit pipeline against one URL — agent loop, scoring, JSON + HTML report.explore_urlYou want a quick autonomous run with a free-form goal; no scenario YAML needed.seeYou want to look at a URL once and get back DOM summary + screenshot + console errors + an optional natural-language note. 0 LLM cost when `goal` is omitted.actYou want to drive an action sequence (click / fill / scroll / screenshot / natural-language `act` / vision `note`) and get back per-step status + final DOM + screenshot.extractYou want a typed payload back from a URL — pricing tiers, feature lists, FAQ entries — shaped exactly the way you asked for. Hand the tool a JSON Schema; get back `data` matching it plus DOM / console / screenshot.judgeYou want a rubric-driven critique of one URL — aesthetic polish, dark-pattern risk, or any custom rubric. Returns per-criterion scores (0..10) + severity-graded findings with on-screen locations. 1 vision call.compareYou want an A/B comparison of two URLs against the same rubric. Default `double_blind` mode judges each side independently then synthesises a comparison (3 vision calls, free of anchoring bias). `fast` mode is 1 call (cheaper, anchored).list_personasDiscover which personas are installed in a project.list_scenariosDiscover which scenarios are installed in a project.list_capabilitiesSelf-describe the server: every shipped tool with kind / cacheability / static cost band / side-effects / dependency declarations, plus the public env-var table and live result-cache state. Pure introspection — call it once on first connect to plan the rest of your session.calibrate_criticRun the critic calibration gate against labeled fixtures (returns pass/fail + agreement metrics).get_last_reportRead the most recent audit's summary JSON from the local history DB.
MCP Server Browser tools 23
browser_clickClick an element on the page, before using the tool, use `browser_get_clickable_elements` to get the index of the element, but not call `browser_get_clickable_elements` multiple timesbrowser_closeClose the browser when the task is done and the browser is not needed anymorebrowser_close_tabClose the current tabbrowser_evaluateExecute JavaScript in the browser consolebrowser_form_input_fillFill out an input field, before using the tool, Either 'index' or 'selector' must be providedbrowser_get_clickable_elementsGet the clickable or hoverable or selectable elements on the current page, don't call this tool multiple timesbrowser_get_download_listGet the list of downloaded filesbrowser_get_markdownGet the markdown content of the current pagebrowser_get_textGet the text content of the current pagebrowser_go_backGo back to the previous pagebrowser_go_forwardGo forward to the next pagebrowser_hoverHover an element on the page, Either 'index' or 'selector' must be provided- +11 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Pixelcheck
{
"mcpServers": {
"pixelcheck": {
"command": "npx",
"args": [
"-y",
"pixelcheck"
],
"env": {
"ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE"
}
}
}
}
MCP Server Browser
{
"mcpServers": {
"agent-infra-mcp-server-browser": {
"command": "npx",
"args": [
"-y",
"@agent-infra/mcp-server-browser"
]
}
}
}
Frequently asked questions
Pixelcheck is categorized under Browser Automation and uses a local stdio subprocess. MCP Server Browser belongs to Browser Automation and uses a local stdio subprocess. Pick Pixelcheck for browser automation work and MCP Server Browser for browser automation.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Pixelcheck has no declared pricing — check the project's own site. MCP Server Browser is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add pixelcheck and agent-infra-mcp-server-browser as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Pixelcheck has a quality signal of 57/100 (Good) with 0 views, 0 installs and 6 GitHub stars. MCP Server Browser has 67/100 (Great) with 6 views, 0 installs and 39,368 GitHub stars.
