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
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
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.
CCR_AGENT_PROXY_ENABLEDCODESPACESDISPLAYE2B_SANDBOX_IDGLASSBOX_ACTIVE_WINDOW_MSGLASSBOX_CHROMEGLASSBOX_CHROMIUMGLASSBOX_CLIENTclient <id> / Who you are. Sessions are owned by whoever opened them; the MCP shim sets mcp-<pid> automaticallyGLASSBOX_EGRESS_CANARYGLASSBOX_HANG_MSEnv knobs. GLASSBOX_SESSION (default session), GLASSBOX_SETTLE_CAP_MS,GLASSBOX_HEADLESSGLASSBOX_HIDE_SCROLLBARSthe flag back, and =1 restores the old behaviour for anyone diffingGLASSBOX_HOMEset to prevent exactly this. None of the thirteen tests do. What actually protectsGLASSBOX_IDLE_TTL_MS(when an in-flight request is called hanging), (idle-session GC).GLASSBOX_LOCALEGLASSBOX_NO_OPENGLASSBOX_PLATFORMGLASSBOX_SESSIONoutput; -s <session> (or ) names the session.GLASSBOX_SETTLE_CAP_MSverify says settled:false. The cap (8s, ) elapsed with a phase stillGLASSBOX_TZGLASSBOX_XVFB_DISPLAYGLASSBOX_XVFB_SCREENMSYSTEMPLAYWRIGHT_BROWSERS_PATHWAYLAND_DISPLAYXDG_STATE_HOMEDependencies
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.
[](https://m8ven.ai/mcp/adihebbalae-glassbox-x2u04a)?variant=verified to the badge URL.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