C
Emerging
74/100
9 days ago

Glassbox

An instrumented local browser daemon MCP server that lets coding agents verify UIs in one call, with console, network, layout, accessibility, and coverage checks, plus debugging tools. It provides named isolated sessions and a CLI+MCP duality for the same verbs.

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

Code Verified⚡ Live Monitored: not connected

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

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

adihebbalae

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 →

Install from

M8ven verifies MCPs across every public registry — install directly from whichever one you prefer.

// key findings
No credential exfiltration, no sensitive file access, no obfuscation
Static analysis found nothing flowing your secrets to unexpected places.
Open source with a license and README
Anyone can audit the code, the license is declared, and the publisher documents what it does.
// 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.
configCCR_AGENT_PROXY_ENABLED
configCODESPACES
configDISPLAY
configE2B_SANDBOX_ID
configGLASSBOX_ACTIVE_WINDOW_MS
configGLASSBOX_CHROME
configGLASSBOX_CHROMIUM
configGLASSBOX_CLIENTclient <id> / Who you are. Sessions are owned by whoever opened them; the MCP shim sets mcp-<pid> automatically
configGLASSBOX_EGRESS_CANARY
configGLASSBOX_HANG_MSEnv knobs. GLASSBOX_SESSION (default session), GLASSBOX_SETTLE_CAP_MS,
configGLASSBOX_HEADLESS
configGLASSBOX_HIDE_SCROLLBARSthe flag back, and =1 restores the old behaviour for anyone diffing
configGLASSBOX_HOMEset to prevent exactly this. None of the thirteen tests do. What actually protects
configGLASSBOX_IDLE_TTL_MS(when an in-flight request is called hanging), (idle-session GC).
configGLASSBOX_LOCALE
configGLASSBOX_NO_OPEN
configGLASSBOX_PLATFORM
configGLASSBOX_SESSIONoutput; -s <session> (or ) names the session.
configGLASSBOX_SETTLE_CAP_MSverify says settled:false. The cap (8s, ) elapsed with a phase still
configGLASSBOX_TZ
configGLASSBOX_XVFB_DISPLAY
configGLASSBOX_XVFB_SCREEN
configMSYSTEM
configPLAYWRIGHT_BROWSERS_PATH
configWAYLAND_DISPLAY
configXDG_STATE_HOME
// quality suggestions

Dependencies

2 dependencies, 1 flagged: playwright

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 — gb_session (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gb_goto (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); gb_act (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.

Tool test coverage

Only 0/14 tools referenced in tests (0%)

Write tests that reference each tool by name so every tool has at least one test.

Shell command execution

18 child_process/subprocess calls in production code — runs shell commands (spikes/cdp-spike.mjs:28, spikes/debugger-spike.mjs:32, spikes/observation-spike.mjs:17)

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

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/adihebbalae-glassbox-x2u04a)](https://m8ven.ai/mcp/adihebbalae-glassbox-x2u04a)
Shows your grade and updates automatically. Prefer no grade? Append ?variant=verified to the badge URL.
commit: a1069f9df893850d6ce320d1125000dd94c9a5dc
code hash: 3ca401b58200450c74e12816a25ebeba222dcd9630f74277a8e5302c5c6d7ba9
verified: 8/10/2026, 4:07:30 AM
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