Listed from the MCP registry; nobody on Odel publishes it.

MCP server: One MCP server.

sniff

@aboudjemRun by its publisher: served from their own domain, namespace checked by the registry.MCP server · External

Find broken pages in your running web app before users do. Each page bug comes with steps and a fix.

Software testingv0.9.5Apache-2.0TypeScript
Freeno charge per call

Runs on your machine from its package; the steps are below.

sniff walking a buggy app and streaming findings with severity, confidence, steps to reproduce, and a fix
From the README

What it does

  1. Reads
  2. Writes
  3. High impact

At most: moves money, runs code or commands, deletes data, or sends messages for you.

What it costs

Free

Odel charges nothing per call. The publisher may charge for its own service.

Runs locally over stdio

This server isn't hosted — your MCP client launches it from a package registry. Use one of the commands below, or drop the config into your client (e.g. Claude Desktop).

npmsniff-qav0.9.5

Run

npx -y sniff-qa

MCP client config

{
  "mcpServers": {
    "sniff": {
      "command": "npx",
      "args": [
        "-y",
        "sniff-qa"
      ]
    }
  }
}
README10 min read
sniff: find broken pages before users do. A map of app pages where the browser walk reaches /crash, which returns HTTP 500, with its two repro steps. Three chips: bugs caught before users, steps to repeat it, broken merges blocked. The command npx sniff-qa --url http://localhost:3000, and the works-with line.

npm version CI License Apache 2.0

English · 简体中文 · 日本語 · Español · Français

Catch broken pages in your web app before users do.

sniff opens your running app in a real browser and clicks like a user.

Bugs caught before usersSteps to repeat itBroken merges blocked
Found 21 of 21 planted bugs, 0 false findings: npm run build && npm run proof.Each page bug comes with its route, the steps to repeat it, and a fix.--fail-on exits 1 on critical or high bugs, so CI stops the merge.

Works with: any MCP client, any agent that reads skills, or the command line alone. MCP is how an agent calls a tool.

Tested: Claude Code, Codex CLI. The walk uses a browser, not a model.

  • What it is: a bug finder for your running web app. You write no tests.
  • When to use it: after you change code, before you merge or ship.
  • What you get: a verdict first, then each bug with its route, steps and a fix.
bash
npx sniff-qa --url http://localhost:3000

What you get

A real report from this repo's test app with planted bugs (2026-11-17, sniff 0.9.3):

text
  VERDICT  FAIL: 26 findings (1 critical, 13 high, 11 medium, 1 low), 1 low-confidence finding hidden
  Walked 12 pages, checked 13 links, in 55.2s. --all shows the hidden one.

  Fix these first:
    1. Page returns HTTP 500 on /crash  [critical]
    2. Page returns HTTP 404 on /dead  [high]
    3. Page returns HTTP 404 on /missing  [high]

  Every finding, with the steps that reproduce it:

  CRITICAL (1)
    • [confirmed] Page returns HTTP 500
      /crash  (route/broken-page)
        - Navigate to /crash
        - Server responded with HTTP 500
      fix: The route throws server-side. Check the server logs/handler for this path and return a valid page or a proper error page.
      shot: sniff-reports/crawl/_crash-desktop.png

Use a dev or staging app: a walk clicks buttons and submits real forms.

What you get · Install · How it works · Works with · Proof · FAQ · Limits

Install

Try it with no install. Start your app, then walk it from a second terminal:

bash
npx sniff-qa --url http://localhost:3000

The npm package is sniff-qa. Do not run npx sniff: that is an unrelated package.

Recommended: the Vercel skills CLI. npx skills is Vercel's open installer for agent skills.

bash
npx skills add Aboudjem/sniff -g

Works in more than 70 agents: pick yours in the menu (supported agents). In a terminal it shows the agent menu. In a script it installs into every agent folder, so add -a <agent> there. -g installs for all your projects. Only this project: drop -g. It installs the 3 skills only. The MCP server is a separate one-line step, shown below.

skills.sh: sniff on the Vercel skills directory skills.sh/aboudjem/sniff

Or install straight into one agent. Node.js 22 or newer.

Claude Code Codex Cursor Gemini CLI GitHub Copilot OpenCode

Claude Code

Install tested.

bash
npx skills add Aboudjem/sniff -g -a claude-code

MCP server, tested, for all your projects:

bash
claude mcp add -s user sniff-qa -- npx -y sniff-qa --mcp

Only this project: drop -s user.

Codex

Install tested.

bash
npx skills add Aboudjem/sniff -g -a codex

MCP server, tested, for all your projects:

bash
codex mcp add sniff-qa -- npx -y sniff-qa --mcp

Cursor

Install tested.

bash
npx skills add Aboudjem/sniff -g -a cursor

Gemini CLI

Install tested.

bash
npx skills add Aboudjem/sniff -g -a gemini-cli

Or add the extension, which brings the MCP server too (install tested):

bash
gemini extensions install https://github.com/Aboudjem/sniff

GitHub Copilot

Install tested.

bash
npx skills add Aboudjem/sniff -g -a github-copilot

OpenCode

Install tested.

bash
npx skills add Aboudjem/sniff -g -a opencode

Claude Code plugin

Adds the skills and the MCP server in one step, through the 10x marketplace:

bash
claude plugin marketplace add Aboudjem/10x
claude plugin install sniff@10x

Any other MCP client runs npx -y sniff-qa --mcp. Snippets for each editor are in docs/editors.md.

First run

The first walk downloads about 440 MB once. On a Mac it uses about 730 MB of disk. It gets the browser engine (Playwright, axe-core and Lighthouse) and Chromium, the browser itself. To do it ahead of time, run:

bash
npx sniff-qa install

It ends with the time it took. On a Mac with empty caches it printed 43 s (2026-11-17, sniff 0.9.3). It left 193 MB of engine and 530 MB of Chromium on disk. Sizes vary by platform. To re-measure on macOS:

bash
du -sm ~/.cache/sniff-qa/engine/* ~/Library/Caches/ms-playwright

npx sniff-qa doctor checks Node, the browser and your dev server.

The MCP server starts before those downloads. With an empty npm cache, npx -y sniff-qa@0.9.1 --mcp answered its first request in 3.1 to 4.9 s (5 runs, 2026-11-17). Version 0.9.0 took 37 to 93 s, past Claude Code's 30 s connect limit. To re-measure, in a clone of this repo:

bash
npm run cold-start -- 0.9.1 5

A walk prints progress lines, then the report. You can take the result four ways:

OutputFlagUse it for
Terminal report(default)Reading the result now
HTML page--reportSharing: one file with everything inside
JSON--jsonScripts and other tools
Exit code--fail-onFailing CI on real bugs
Exit codeMeaning
0No finding reached the --fail-on severities (default: critical and high)
1A finding reached them, an assert limit was passed, or sniff could not run
Project install and CI

To block bad merges, use --fail-on in CI. Its default is critical and high. npm install -D sniff-qa adds it to a project. npx sniff-qa ci writes a GitHub Actions workflow that caches the browser and saves the report. With no app running, its first run only reads your source. Turn on its Start the app step (remove the #) and add --url to walk the app.

How it works

Example: you change one form, and a page you never opened now shows a server error (HTTP 500). The walk reaches the pages your links lead to, so it can find that error before users do.

sniff walking a buggy app and streaming findings with severity, confidence, steps to reproduce, and a fix How sniff works: crawl, act, assert, prove, report
  1. Find the app. It uses --url, or a dev server on a common port.
  2. Walk it. Chromium, with no window, follows your links, clicks buttons and fills forms, like a user.
  3. Judge what happened. Each page is checked for 12 classes of bugs.
  4. Prove it. A finding needs a route and the steps. It adds a screenshot and the console or network lines when it has them.
  5. Report. Verdict first, then the fix-first list, then the detail.

The 12 classes:

The 12 classes of bugs sniff finds

With no app running, sniff reads your source instead (sniff scan). It flags debug statements, placeholder text and broken imports, and tells you how to start the real walk.

The MCP server gives your agent these tools:

ToolWhat it does
sniffOne entry point: mode: "walk", "scan" or "report"
sniff_scanSource-only scan, no browser
sniff_runSource scan plus browser checks
sniff_discoverWrites test paths from your source and runs them
sniff_installDownloads the engine and Chromium, with progress
sniff_reportReads the last saved results

--caps scan,report limits the server to sniff_scan, sniff_report and the main sniff tool. Then it uses no browser at all.

Works with

Each row was tested on 2026-11-17. The first five used the sniff 0.9.0 build, the install rows used 0.9.4.

AgentWhat ranTested
Claude Codeclaude -p with sniff as an MCP server called sniff_scan and read 2 findings2026-11-17
Codex CLIcodex exec with sniff as an MCP server called sniff_scan and read 2 findings2026-11-17
Gemini CLIgemini extensions validate . accepted gemini-extension.json2026-11-17
Any MCP clientnode sniff-tests/mcp-smoke.mjs listed 6 tools and a walk returned 20 findings2026-11-17
Skills CLInpx skills@1.9.0 add Aboudjem/sniff installed the 3 skills into a temp folder2026-11-17
Claude Codeclaude mcp add -s user wrote sniff-qa into a throwaway home's .claude.json2026-11-17
Codex CLIcodex mcp add wrote sniff-qa into a throwaway home's config.toml2026-11-17
Gemini CLIgemini extensions install installed and enabled sniff in a throwaway home2026-11-17
Cursorskills add -g -a cursor put the 3 skills in a throwaway ~/.agents/skills2026-11-17
GitHub Copilotskills add -g -a github-copilot put the 3 skills in ~/.agents/skills2026-11-17
OpenCodeskills add -g -a opencode put the 3 skills in ~/.agents/skills2026-11-17
Claude Codeskills add -g -a claude-code put the 3 skills in ~/.claude/skills2026-11-17
Codex CLIskills add -g -a codex put the 3 skills in ~/.agents/skills2026-11-17
Gemini CLIskills add -g -a gemini-cli put the 3 skills in ~/.agents/skills2026-11-17
Skills CLIskills add -g with no terminal installed into every agent folder2026-11-17

Documented, not tested today: Windsurf and Zed. Cursor, Copilot and OpenCode were install tested only. Their snippets are in docs/editors.md.

Proof

These commands re-print the numbers on this page. The first prints the score on the test app.

bash
npm run build && npm run proof

It starts the planted-bug test app, walks it, and scores the report. Output on 2026-11-17:

text
  Recall:    21/21  (100%)
  Findings:  27 deduped (27 raw)
  Matched:   27   Candidate FP: 0   Precision proxy: 100%
  Hard FP on clean page (/clean): 0

The sample above shows 26 findings and says 1 low-confidence finding is hidden. The proof run uses --all, so it counts all 27.

The test app holds 21 bugs added on purpose (planted bugs) across all 12 classes. It also has one clean page with no bug. The scorer is sniff-tests/score-fixture.mjs. The bugs are listed in sniff-tests/planted-bugs/MANIFEST.json.

To get the same report as the sample, start the test app. Then run sniff in a second terminal:

bash
node sniff-tests/planted-bugs/server.mjs 4517
npx sniff-qa --url http://localhost:4517
bash
npm test

Prints Test Files 54 passed (54) and Tests 603 passed (603) on 2026-11-17. The suite includes a gate on the test app. It fails the build if sniff finds fewer than 85% of the planted bugs. It also fails if sniff reports anything on the clean page.

bash
node sniff-tests/mcp-smoke.mjs

Prints the 6 MCP tools and the 20 findings quoted in the table above.

FAQ

Do I need an API key or an account? No. The walk and the source scan run on your machine. Nothing is sent anywhere unless you set up the optional AI exploration yourself.

Will a walk change data in my app? It can. A walk clicks buttons and submits real forms, so point it at a dev or staging app.

Why did it exit 1 when nothing crashed? Exit 1 means it found bugs at a failing severity, so CI fails the build. Pass --fail-on none to always exit 0.

Will it edit my code? No. Walking and scanning never touch your source. Only sniff fix edits files, and only when you run it.

Can it walk a logged-in app? Yes. Pass --storage-state auth.json. Cookie and token values from that file are hidden in the written reports.

More answers are in docs/faq.md.

Limits

  • It needs a running app for the walk. Without one you only get the source scan.
  • The first walk needs internet to download the engine and Chromium once: about 440 MB, then about 730 MB on disk on a Mac.
  • Until then, MCP browser tools answer needsSetup and the agent calls sniff_install first.
  • Dead-link checking follows external links, so a walk requests the third-party URLs your pages link to.
  • Hiding secrets covers report text, not screenshots. A screenshot of a logged-in page can show private data.
  • It finds what a user would see. It does not read your server logs or measure load.

Learn more


Built by Adam Boudjemaa · Apache 2.0 · built on Playwright and axe-core

Similar modules

Browse Software testing