UX testing inside
Claude Code,
Cursor, and Codex
Swarm’s MCP server gives your AI coding editor a real testing loop. AI personas navigate your localhost, find friction, and feed structured UX issues back into the chat. The model that wrote the code is the one that sees it break.
Included on Pro ($50/mo) and Business. Not on the Free tier.
Streaming findings from 5 personas...
01 / Install
One command.
Every editor.
The Swarm MCP server is published to npm as @useswarm/mcp. The setup command registers Swarm with every MCP-capable editor it detects and signs you in over a browser flow.
- Runs locally over stdio
- Credentials stored at ~/.useswarm/config.json
- No source code leaves your machine
Auto-configured by the setup command. Restart the editor and you are done.
$ npx @useswarm/mcp@latest setupDetects Claude Code and Codex CLI automatically. Add --client claude to scope to one editor.
02 / How it works
From prompt to findings,
without leaving chat.
The MCP server runs locally over stdio. It tunnels your localhost through Cloudflare so Swarm’s cloud agents can reach your dev server. No code leaves your machine.
- 01
You prompt your editor
In Claude Code or Cursor, you write a one-line request. The model recognizes it as a Swarm tool call and invokes dev_test with a target URL, a goal, and an audience.
prompt“Test localhost:3000. Goal: complete signup.”
- 02
The MCP tunnels your localhost
The local MCP server opens a short-lived Cloudflare tunnel so Swarm's cloud-hosted agents can reach your dev server. The tunnel closes when the test ends.
tunnellocalhost→cloudflare→swarm - 03
AI personas navigate your app
Personas matching the audience you described navigate the flow. They click, type, scroll, and read the page like real users, surfacing confusing copy, broken interactions, and drop-off points.
personasJDARMSTK+1 - 04
Structured issues stream back
Your editor receives a stream of UX findings as they happen. Each finding has a severity, a description, the step it occurred at, and a specific suggested fix.
findingPassword rules hidden until errorStep 2 of 5 · severity: medium - 05
Fix, then re-test
When the model edits code and the dev server reloads, you can re-run the same test with one line. Same audience, same goal, see whether the issues are gone.
re-run$ same flow+ 0 new issues↺ 1m 32s
03 / The surface area
The tools your editor gets.
Once the MCP is connected, the model can call these as part of its normal tool-use loop. You don’t have to memorize them. Just ask the editor to test something.
Start a test run. Takes a target URL, a goal in plain English, and an optional audience description.
Stream structured UX issues as the personas find them. Each finding includes a severity, location, and suggested fix.
Check progress on an in-flight test. How many personas have run, how many issues found so far.
List the recent test runs for this project. The model uses this to pick up where it left off across sessions.
End an active session and tear down the Cloudflare tunnel. Called automatically when a test completes.
04 / In practice
What teams ship it for.
“Test the signup flow you just shipped. Audience: first-time SaaS users.”
Test the flow you just wrote
After Claude or Cursor writes a new signup, checkout, or onboarding flow, ask it to test what it just shipped before you reload the page yourself.
“Same test as last time. Did anything break?”
Catch regressions while iterating
When you refactor, the model reruns the last test against your dev server and tells you whether anything broke, without a full QA cycle.
“Verify the new CTA copy actually lands with target audience.”
Validate AI-generated UI
When the model proposes a UI change, it can verify that real personas in the target audience actually understand and click through.
05 / Common questions
Frequently asked.
Setup, security, supported editors, and what each plan unlocks. For anything else, email the founders.
An MCP server is a process that speaks the Model Context Protocol, an open standard from Anthropic that lets AI tools like Claude Code, Cursor, and Codex call external tools and read external data. Swarm's MCP server exposes UX testing tools so your AI coding assistant can run real usability checks against your app without leaving the editor.
Ship code, then test it
from the same chat.
MCP access is included on Pro ($50/mo) and Business. Pro gives you 20 live agent runs per month, plus 50 screenshot runs. Enough to wire the loop into your editor and keep testing as you ship.