Enables AI agents to perform automated UX reviews by navigating apps in a browser and generating reports on usability issues.
Also known as carlosphyll/phyll
- Stars
- 2
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.4.6
- Last commit
- Nov 13, 2026
- License
- MIT
What is Phyll MCP?
Phyll enables AI agents to perform automated UX reviews by navigating apps in a browser and generating reports on usability issues.
Summary generated from the project's README
About Phyll MCP server
Phyll allows AI agents to conduct automated usability audits by interacting with applications through a real browser. It works with MCP-compatible clients like Claude Code, Cursor, Windsurf, Gemini CLI, and Codex. Once configured, your agent acts like a new user, navigating through core workflows to identify friction points such as excessive form fields, sign-up barriers, non-functional buttons, or poor text contrast.
The setup process requires Node 20 or newer and involves running specific setup commands to register the connector in your agent's configuration files and install a Chromium build. While the AI processing happens locally on your own plan, the connector communicates with the Phyll engine to manage review methods and store reports. Users can manage their usage, keys, and subscriptions through the command line or the web dashboard. A free account includes five full reviews, while a Pro subscription offers unlimited reviews.
What you can do with it
- 1Automated usability testingAsk your AI agent to perform a full review of a running local application to find UX issues.
- 2Identify design frictionUse the agent to detect specific usability problems like dead buttons or hard to read text.
- 3Source code scanningScan your project files to find specific indicators intended for AI.
- 4Visual route auditingCapture screenshots and page data for different routes at both mobile and desktop sizes.
Written from the project's README. Every use case is checked against a quote from it.
How to install Phyll MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Phyll MCP in Claude Code
$ claude mcp add phyll -- npx -y phyllInstall Phyll MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"phyll": {
"command": "npx",
"args": [
"-y",
"phyll"
]
}
}
}Install Phyll MCP in VS Code
.vscode/mcp.json
{
"servers": {
"phyll": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"phyll"
]
}
}
}Install Phyll MCP in VS Code CLI
$ code --add-mcp '{"name":"phyll","type":"stdio","command":"npx","args":["-y","phyll"]}'Install Phyll MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"phyll": {
"command": "npx",
"args": [
"-y",
"phyll"
]
}
}
}Install Phyll MCP in Codex
$ codex mcp add phyll -- npx -y phyllInstall Phyll MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.phyll] command = "npx" args = ["-y", "phyll"]
Install Phyll MCP in Gemini CLI
$ gemini mcp add -s user phyll npx -- -y phyllInstall Phyll MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"phyll": {
"command": "npx",
"args": [
"-y",
"phyll"
]
}
}
}Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablecarlosphyll/phyll is public and reachablegithub.com/carlosphyll/phyll ↗Pass
- Package names this repository as its sourcephyll names carlosphyll/phyll as sourcenpmjs.com/package/phyll ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for phyllnpmjs.com/package/phyll/v/0.4.6#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/carlosphyll/phyll ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from phyllPass
- No critical advisory in the package or its dependencies101 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubphyll
UX review for apps built with AI, inside the agent you already use.
Phyll plugs into Codex, Claude Code or any agent that speaks MCP. Your agent opens your app the way a first-time user would, walks the core jobs in a real browser, and writes a report of what gets in the way: forms that ask for more than the job needs, sign-up walls, dead buttons, text too faint to read. The fixes keep your design.
The AI work runs in your agent, on your own plan. This package adds the browser, the page probe, the source scanner and the link to Phyll's engine, which sends the review method, checks the report and keeps it with a link.
Start
npx phyll signup you@example.com
npx phyll setup codex # or claude, cursor, windsurf, gemini
Then ask your agent: "review my app at http://localhost:3000".
setup registers the connector in Codex's config.toml, with claude mcp add, or in the mcpServers of Cursor's ~/.cursor/mcp.json, Windsurf's ~/.codeium/windsurf/mcp_config.json or Gemini CLI's ~/.gemini/settings.json, keeping everything else in the file. It also installs the Chromium build the connector uses. For any other agent that takes MCP servers, npx phyll setup other prints the entry to paste. You need Node 20 or newer.
Your reports, keys and plan are also on the site: npx phyll account opens your account there, already signed in. If you lose the key, sign in at agentphyll.com/login with your email and create a new one.
Commands
| Command | What it does |
|---|---|
signup <email> |
Create a free account, with 5 full reviews. The key is saved in ~/.phyll |
login <key> |
Use an account you already have on this computer |
setup <agent> |
Connect Phyll to codex, claude, cursor, windsurf or gemini and install the browser; setup other prints the settings for any other agent |
status |
Your plan and the reviews left |
account |
Open your account on agentphyll.com, already signed in: reports, usage, keys and plan |
pro |
Subscribe to Phyll Pro, R$ 9 a month, with unlimited reviews |
billing |
Change the card or cancel Phyll Pro |
scan [folder] |
Scan the source for AI tells, with no account and no AI. --format json for scripts, --format badge for a README badge |
mcp |
Run the connector for your agent; setup registers it for you |
logout |
Forget the key on this computer |
The tools your agent gets
start_review scans the project, creates the report folder and returns the method. capture saves a screenshot and the page probe of each route at laptop and phone size. open, snapshot, click, fill, select, check, press, back, screenshot, probe and resize drive the browser, which stays on your app. guide returns a part of the method, finish_review sends the report to the engine and writes report.md, and scan, account and upgrade do what their names say.
What leaves your computer
Your source code, your screenshots and your agent's conversation stay on your computer. When a review starts, the connector sends the app's address, the project name and a summary of the scan: which tells it found, how many times, and the paths of routes and forms. When it ends, it sends the report your agent wrote, which the engine keeps so the link works.
More
The scanner, the plugin and four example apps are in the repository. MIT license.
Phyll MCP questions
How do I add Phyll MCP to Claude Code?
Run claude mcp add phyll -- npx -y phyll in your terminal. Add --scope user to make it available in every project.
How do I add Phyll MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I start a UX review with my agent?
After setting up the connector, you can simply ask your agent to 'review my app at [your URL]'.
What information is sent from my computer to the Phyll engine?
The connector sends the app's address, project name, a summary of the scan (tells found, frequency, and paths), and the final report written by your agent.
Does my source code leave my machine during a review?
No, your source code, screenshots, and agent conversations remain on your local computer.