glovebox
NPM · @VASHP2029/GLOVEBOX
Computer use for coding agents on macOS: JS scripts, accessibility diffs, background input.
Available components
Last scanned (2 hours ago)
Scores higher than 35% of npm servers
Category Developer Tools
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security100
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 0 of 1 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency48
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability59
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 538 tokens (~269/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Unverified: 1 category
A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 5 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 4 Nov 26 53
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Analysed npm/@vashp2029/glovebox@0.3.2
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 1 package
| Packages resolved | 1 |
|---|---|
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
js ~479
Run JavaScript in a persistent computer-use session. Put a whole step in one call: several actions, then one read. Top-level const/let/function/await persist across calls until js_reset (redeclaring is fine). const calc = await gb.getApp("Calculator"); // name, bundle id, or "pid:123"; launches if needed, does not steal focus await calc.pressKey("Escape"); // xdotool syntax: Return, Tab, ctrl+a, super+c (super = Cmd) await calc.typeText("12*3="); // "\n" presses Return await calc.getAXState(); // text accessibility tree; later reads return only changes Reads: getAXState({disableDiffing, frames, menus, window}) returns "<index> <role> \"label\" value=..." lines. frames:true adds @x,y wxh in image pixels. getScreenshot() and getAXStateAndScreenshot() are the only calls that return an image. Every read emits its output; pass {emit:false} to just get the value. Actions: click(target, {button, count, modifiers}), doubleClick, rightClick, scroll(target, dy), drag(from, to), setValue(index, v), focus(index), selectText(index, {start, length}), performSecondaryAction(index, "Show Menu"), listActions(index), activate(), windows(), frame(index), center(index). A target is an element index from the tree, or [x, y] pixels in the window image (same space as the screenshot and frames). Prefer indices; use pixels when the tree has nothing useful (remote desktops, canvases). Input stays in the background (focus and the user's cursor don't move); pass {foreground: true} to an action if an app ignores it. gb.listApps() lists running apps. console.log adds text to the result. help() or help("click") prints the full API. If a result says "Stopped:" the user took over (switched apps or pressed Escape): stop and ask before continuing.
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | JavaScript to run. Top-level await is supported. |
| timeout_ms | integer | – | Time limit in milliseconds (default 120000). |
| title | string | – | A few words naming this step, for the action log. |
No output schema declared.
No examples provided.
js_reset ~29
Restart the session and drop every binding. Use when a script is stuck or you want a clean slate.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the glovebox MCP server?
glovebox runs locally as an npm package, launched with npx -y @vashp2029/glovebox. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @vashp2029/glovebox
claude mcp add vpatel9202-glovebox -- npx -y @vashp2029/glovebox
What is the glovebox MCP server?
glovebox is an MCP server listed in the public MCP registry as io.github.vpatel9202/glovebox. Computer use for coding agents on macOS: JS scripts, accessibility diffs, background input. This page covers its npm package (@vashp2029/glovebox).
Is the glovebox MCP server safe to use?
glovebox scores 68 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the glovebox MCP server expose?
glovebox exposes 2 tools: js, js_reset. Their descriptions and schemas cost roughly 508 tokens of context every time the server is loaded.
Is the glovebox MCP server still maintained?
glovebox is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the glovebox MCP server under?
glovebox declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.