GlanceCAUTION
AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Glance
AI-powered browser automation for Claude Code by DebugBase
Navigate, click, screenshot, test — all from your terminal.
What is Glance?
Glance is an MCP server that gives Claude Code a real browser. Instead of guessing what your web app looks like, Claude can actually see it, interact with it, and test it.
You: "Test the login flow on localhost:3000" Claude: *opens browser* *navigates* *fills form* *clicks submit* *takes screenshot* *verifies redirect* *checks for errors* "Login flow works. Found 1 console warning about..."
Features
- 30 MCP tools for complete browser control
- Inline screenshots — Claude sees what the browser sees
- Accessibility snapshots — full page structure as text
- Test scenario runner — define multi-step tests in JSON
- 12 assertion types — exists, textContains, urlEquals, and more
- Session recording — record and replay browser sessions
- Visual regression — pixel-level screenshot comparison
- Network & console monitoring — catch errors and failed requests
08792fa352acOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add glance-mcp -- npx -y [email protected]
{
"mcpServers": {
"glance-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (32)
29 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
browser_click | read | |
browser_close | read | |
browser_console_messages | read | |
browser_drag | read | |
browser_evaluate | read | |
browser_go_back | read | |
browser_go_forward | read | |
browser_hover | read | |
browser_navigate | read | |
browser_network_requests | read | |
browser_press_key | read | |
browser_screenshot | read | |
browser_scroll | read | |
browser_select_option | read | |
browser_snapshot | read | |
browser_tab_list | read | |
browser_tab_new | read | |
browser_tab_select | read | |
browser_type | read | |
session_end | read | |
session_list | read | |
session_replay | read | |
session_start | write | |
test_assert | read | |
test_auth_flow | read | |
test_fill_form | read | |
test_scenario_run | write | |
test_scenario_status | read | |
test_stop_watch | write | |
test_watch_events | read | |
visual_baseline | read | |
visual_compare | read |
Trust audit
CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (4)
urlAllowlist: ['http://localhost:*', 'http://127.0.0.1:*', 'https://localhost:*', 'https://127.0.0.1:*', 'http://*', 'https://*'],
urlAllowlist: ['http://localhost:*', 'http://127.0.0.1:*'],
@modelcontextprotocol/sdk, pixelmatch, playwright-core, pngjs, uuid, zod, @types/node, @types/uuid
description: Run E2E browser tests on any web application using Glance MCP. Use when the user says "test this page," "check this URL," "run E2E tests," "browser test," "test the login flow," "check if
Gates applied: no_behavioural_pass.
08792fa352acfull audit observations/trust-audit/mcp-server/debugbase__glance.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 08792fa352ac | CAUTION | B | 89 | first audit |
Questions
What is the Glance MCP server?
AI-powered browser automation MCP server for Claude Code. Navigate, click, screenshot, test — all from your terminal.
What tools does Glance expose?
32 in total: 29 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Glance safe to connect to an agent?
With care. The audit graded it B (89/100) and found 4 things worth knowing before you trust this server, listed below with the exact line each was found on.
What credentials does Glance need?
No credential environment variables were found in its source, so it appears to need none.
How does Glance run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as glance-mcp at 1.1.0.
How current is this page?
The grade is for one exact copy of the source (08792fa352ac), read on 2026-10-07. The repository is watched and re-audited when it changes.