Mimiq: AI agents use your app like your users and find what breaks

victorgulchenko/mimiq-mcp

Connects your AI coding agent to Mimiq's synthetic user testing API. Exposes six tools: test_page for landing pages, test_flow for multi-step interactions like checkout, test_copy for A/B headline tests, and ask_audience for product surveys. Each test runs against simulated personas and returns raw feedback including user actions, internal monologues, and objections. Works with localhost out of the box by automatically spinning up temporary cloudflared tunnels. You get 100 free persona simulations, then 2,000 for $10. Reach for this when you want your agent to catch UX issues and confusing copy during development, not after deployment. Self-hostable if you're running the Mimiq backend yourself.

GitHub stars: 1
tools: 2
transport: HTTP
last updated: Oct 22, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://mcp.mimiqai.com/mcp --name mimiq-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http mimiq-mcp https://mcp.mimiqai.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 2 tools

Verified live against the running server on Nov 6, 2026.

mimiq.show_reportShow a saved Mimiq run: where it stands while it runs (it waits up to 40 seconds for it to end), then what the agents hit, where each stopped and why, and a link to the full report. Use the session ID from an earlier run or a report URL. Reads your account only and spends no c...2 params

Show a saved Mimiq run: where it stands while it runs (it waits up to 40 seconds for it to end), then what the agents hit, where each stopped and why, and a link to the full report. Use the session ID from an earlier run or a report URL. Reads your account only and spends no c...

Parameters* required

compare_session_idstring

session_id*string

mimiq.test_flowUse this after you build or change anything a user goes through (signup, onboarding, checkout, settings, a new feature), on the preview or staging URL, and again after each fix. AI agents, each acting as one of the app's users, open it in their own real browser and try the tas...12 params

Use this after you build or change anything a user goes through (signup, onboarding, checkout, settings, a new feature), on the preview or staging URL, and again after each fix. AI agents, each acting as one of the app's users, open it in their own real browser and try the tas...

Parameters* required

accessobject

Only for a site that is not open to everyone. vercel_bypass: a Vercel "Protection Bypass for Automation" secret for a protected preview. basic_auth: a username and password the site asks for in a b...

audiencestring

Who the simulated people should be, in plain words, e.g. "startup founders in SF" or "parents shopping for kids toys". If omitted, Mimiq picks the likely audience from the content.

audience_correctionstring

Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts unless the new crowd is wrong, otherwise returns a new review.

audience_fit_acknowledgedboolean

Set only after telling the user about an audience-fit warning and they choose to continue.

confirm_audienceboolean

Start with the reviewed people after showing them to the user.

countinteger

How many simulated people (default 5, max 10; without a key a free flow has up to 3, and defaults to 3). Each runs a full browser session and uses 5 credits.default: 5

devicesstring

Which devices the agents use. "mix" (the default): about 4 in 10 on a phone-sized touch screen, the rest on a laptop. "phone" or "laptop" puts every agent on one.one of mix · phone · laptop

goalstring

The task each person tries, e.g. "complete the signup and reach the dashboard". Default: sign up and start using it.

max_stepsinteger

Usually leave this out: each agent keeps going until it finishes the task or gets stuck, within the server's limit. Set it (10 to 200) only to cap a run on purpose.

new_runboolean

Start a new run even if this same test is still running or has a result nobody has read. Use it after you change the build. Uses credits.

review_idstring

The review_id from a low-fit review or completed/running result. Bound to this URL and test kind.

url*string

Where the flow starts. Must be publicly reachable. For localhost, open a cloudflared tunnel and pass the tunnel URL.

Readme

Mimiq MCP Server

Your agent built it. AI agents use it like your users before you ship.

Point Mimiq at a preview or staging URL and a task in plain words, such as signing up or reaching checkout. No test scripts. Each agent acts as one of your users: it opens the app in its own real browser, clicks, types and fills in your forms (with an inbox of its own for verification codes), and the report shows what was broken, what did nothing, where each agent got stuck or gave up and why, with the step and a screenshot. Fix what they hit and run it again on the new build.

Tools

View the full README on GitHub

Details

Repository: github.com/victorgulchenko/mimiq-mcp
Website: www.mimiqai.com/mcp
Transport: HTTP
Registry: MCP registry, active
Resources: 1
Tools verified: Nov 6, 2026