1. Conduid
  2. Blockchain
  3. Visual Inspector MCP
MCP server · Blockchain

Visual Inspector MCP

by · github.com/MatinMHF/visual-inspector-mcp

MCP server that lets Claude Code (or any MCP client) visually inspect rendered web pages via screenshots — navigate, click, resize, and read console logs through a persistent headless Chromium browser

Unclaimed blockchain
InstallView source
34Low

Scored a month ago · breakdown

About Visual Inspector MCP

Visual Inspector MCP is an MCP server published by MatinMHF in the Blockchain category: mCP server that lets Claude Code (or any MCP client) visually inspect rendered web pages via screenshots — navigate, click, resize, and read console logs through a persistent headless Chromium browser.

The repository has 1 stars and 0 forks, with the last commit 3 months ago. Recent commit activity is the strongest signal that reported issues will get attention.

Install

From source
git clone https://github.com/MatinMHF/visual-inspector-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (8)

clickClick an element to reach a UI state (open a modal, menu, tab) before screenshotting it.

Parameters not published.

console_logsRecent browser console messages and page errors, to correlate a visual issue with a JS error. Supports `limit` and an `error`-only filter.

Parameters not published.

fillSet the value of an input/textarea/select by selector (`locator.fill` — clears then types, dispatching the input/change events React controlled components need). Pass `fields` to fill several inputs in one call.

Parameters not published.

navigateLoad a URL (dev server, `file://`, or any public site) in a persistent page. Stays open for subsequent calls. Returns the *resolved* URL + title, so silent redirects are visible.

Parameters not published.

pressPress a keyboard key such as `Enter` (submit a form), `Tab`, or `Escape`, against a given `selector` or the focused element. Supports Playwright key syntax (e.g. `Control+A`).

Parameters not published.

resizeChange the viewport size to check a responsive breakpoint, independent of navigating or screenshotting — so you can resize → click → screenshot without reloading the page (and losing client-side state).

Parameters not published.

screenshotScreenshot the current page, or a single element by CSS selector / Playwright locator syntax (e.g. `text=Submit`). Supports viewport, full-page, and element-scoped capture. Defaults to lossless PNG; JPEG is an opt-in for large, photo-heavy full-page captures.

Parameters not published.

typeType into a field one key at a time (`locator.pressSequentially`), firing a keydown/keypress/keyup per character — for inputs whose handlers need real keystrokes and don't react to `fill`. Optional `clear` and per-keystroke `delay`.

Parameters not published.

Ask AI

✦

Ask AI about Visual Inspector MCP

Powered by Claude · Grounded in docs

I know everything about Visual Inspector MCP. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About Visual Inspector MCP

How do I install Visual Inspector MCP?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Visual Inspector MCP safe to use with an AI agent?

Its trust score is 34 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Visual Inspector MCP still maintained?

Yes — the last commit was 3 months ago. The repository has 1 stars and 0 forks.