MCP.Market

Cmp Inspector MCP server

by kvdm-co-pilot·io.github.kvdm-co-pilot/cmp-inspector·v0.9.1
No reviews yet

Compose Multiplatform UI as structured JSON for agents: trees, tokens, previews, diffs. No pixels.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars60 downloads/wk

Reviews

Write one

Nobody has reviewed Cmp Inspector yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Cmp Inspector tools (15)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • approval_status

    The human-approval half of the console (VERIFICATION-LAYER-DESIGN.md §4): every governed

  • connect_live

    Tier 1 handshake, SELF-HEALING: ensures a device/emulator is attached, ensures the

  • db_query

    GET /inspect/db?table=<name>&limit=<n> on the running app — assert PERSISTED state in the live

  • inspect_tree

    Load the enriched Compose semantics tree (hierarchy + geometry + resolved design tokens) as JSON,

  • navigate_and_inspect

    Drive the LIVE app one tap at a time, no pixels needed: resolves the tap point from the live

  • preview

    AI-native previews of a create-cmp app's REAL screens with NO device, emulator, or

  • preview_diff

    The verified dev loop with ZERO bookkeeping: the preview service already retains the previous

  • preview_status

    The agent's post-edit feedback call. Without arguments: returns the preview service's

  • preview_stop

    Stops the resident preview service started by `preview` (file watcher + gallery server).

  • render_screen

    Pixel preview with a PATH-ONLY contract: returns { path, width, height, sizeBytes,

  • resolve_comment

    Marks a comment resolved via the project's own qa/lib/comments.mjs, recording author 'agent'

  • review_comments

    The human-comment half of the console (VERIFICATION-LAYER-DESIGN.md §7.3: 'pixels flow to the

  • runtime_crashes

    GET /inspect/crashes on the running app (current boot + previous ones; the on-device handler

  • runtime_logs

    Shells `adb shell pidof <appId>` (appId resolved from the live inspector's GET /inspect/health)

  • snapshot_variant

    GENESIS-FLOW-DESIGN.md §2 'Design-language candidates (variants)': copies the CURRENT

Public scan report

scanner v0.1.10 · 2026-11-01 · same rubric, same numbers if you re-run it

no findings
  • Code scan41 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 11 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Cmp Inspector compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
15
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
60
more than 49% of 12,191 servers with a package

What its tools let an agent do: 13 read · 2 run or deploy

Release history: 2 versions in the registry since 2026-08-21, latest 2026-09-26, typically one every 36 days.

Install Cmp Inspector in Claude Code, Cursor or VS Code

Runs npx -y @create-cmp/inspector on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add cmp-inspector -- npx -y @create-cmp/inspector
Add to Cursor

What the publisher says

From the Cmp Inspector repository's README, as published. We do not edit it. Read it on GitHub

create-cmp

The AI delivery harness for Kotlin/Compose Multiplatform.

Gives AI coding agents eyes and a machine-enforced definition of done on mobile: scaffold a green-building Android + iOS app in minutes, then let AI extend it — seeing every screen it renders, and blocked from "done" without proof.

npm create kmp@latest my-app

Deterministic (stamps a frozen, CI-verified template), non-interactive with flags, exits non-zero on failure — and it builds the app to prove it's green before reporting success. Agent-readable: llms.txt · AGENTS.md · options.schema.json.

Claude Code users: /plugin marketplace add kvdm-co-pilot/create-cmp → /plugin install create-cmp — 12 skills + the cmp-inspector MCP server.

What is this, in plain words

One product: a contract between an AI agent and a mobile repo. The agent gets eyes (every screen rendered headlessly as structure, never screenshots), hands (generators that extend the app correctly by construction), and — when you want it — a definition of done it cannot argue with (an executable verify lane, evidence receipts, enforcement). You climb in three steps, each priced in what you have at that moment:

See the trust layer live: create-cmp-showcase is a public repo built entirely by this tool — every commit carries its evidence receipt, and PR #1 shows the harness refusing a bad change and naming the exact rule it broke.

The core loop

spec clause  →  generate from exemplar  →  verify lane  →  evidence receipt
      ↑                                                              │
      └────────────── enforcement: Stop hook + CI refuse "done" without it ──┘

Behavior starts as a written spec clause. Code is cloned from a proven exemplar. The verify lane checks everything — spec coverage, build, tests, architecture, UI structure, design tokens, accessibility, on-device E2E, and more — and writes a receipt bound to a content hash of the code it verified. You cannot hand-forge it, and a stale one doesn't pass.

Quick start

npm create kmp@latest my-app interviews you and takes you through it interactively. For scripts and CI, drive it with flags instead:

npx create-cmp-cli@latest my-app --name Acme --package com.acme.app --yes --verify

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Cmp Inspector: common questions

Is Cmp Inspector MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Cmp Inspector safety report
How do I install Cmp Inspector?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Cmp Inspector need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Cmp Inspector maintained?
The last commit was 14 days ago (2026-10-21). The latest release is v0.9.1.
How does Cmp Inspector compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 15 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.