Glance (Browser MCP)

Name: Glance (Browser MCP) Review
Item: Glance (Browser MCP)
Rating: 3.0
Author: Aaron Matthews

Connector Development Usable

Works inClaude Code Claude Cowork Claude Chat

Usable Scanned — metadata only

Browser testing directly from Claude Code without leaving the terminal. Used in production at DebugBase with 300+ test steps at 97% pass rate.

Open-source MCP server giving Claude Code a real Chromium browser with 30 tools — navigate, screenshot, click, fill forms, run E2E tests, and visual regression testing from the terminal.

Write and run browser tests against live web pages
Take screenshots and fill forms during automated testing
Catch visual regressions by comparing page screenshots

154 starsMIT (commercial OK)FreeNo code needed

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Browser testing directly from Claude Code without leaving the terminal. Used in production at DebugBase with 300+ test steps at 97% pass rate. Fills a real gap for frontend developers.

Best for

Frontend developers and QA teams who want Claude to write and run browser tests. Competes with Playwright MCP but offers a more visual, screenshot-driven approach.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/DebugBase/glance

By DebugBase

How to Get It

Option 1: Claude Desktop AppOpen the Customize panel in the sidebar → browse connectors → search and add. Works in Claude Code, Claude Cowork, and Claude Chat.

Option 2: Paste into Claude CodeCopy the command below and paste it into a Claude Code conversation. Claude will run it for you.

Command

claude mcp add glance -- npx glance-mcp

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

First thing to try

Once it’s connected, paste this into Claude:

Help me write and run browser tests against live web pages

PrerequisitesNode.js/npm (server distributed as npm package glance-mcp)CostFree

Trust Signals Auto-scanned

Stars154Contributors1Last updated2026-04-16LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-07-20 · scanner vattempted-no-data

Data & Access

Data processingPrompts sent to Anthropic API. Enterprise/Team plans exclude training.

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 155 GitHub stars; 1 contributors; last commit 82d ago; license MIT.

Things to check

Browser automation tools carry inherent security surface. Verify the tool does not expose browser state or saved credentials to Claude. 97% pass rate means 3% failure — review failure modes.
Single maintainer. Consider the risk if this person stops maintaining the project.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

3/5

Reliability

3/5

Security

3/5

Overall score3.00 / 5.00 UsableEvaluatedJul 2026

catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 155 GitHub stars; 1 contributors; last commit 82d ago; license MIT.

← Back to the Claude Observatory