Skip to content

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

io.github.victorgulchenko/mimiq-mcpvictorgulchenkostreamable-httpv0.5.1Scanned

AI agents use your app like your users, in real browsers, and report what is broken or confusing.

2 tools: 1 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 1 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 1
  • Can send data out · 1
  • No findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here changes things. Govern it.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the Mimiq: AI agents use your app like your users and find what breaks MCP server can do

The Mimiq: AI agents use your app like your users and find what breaks MCP server is published by the GitHub account victorgulchenko. It has 2 tools. It can create or change data (1 tool: mimiq.test_flow), but cannot delete data. 1 tool only reads.

1 tool brings in text other people can write (mimiq.test_flow); 1 tool can send data out of your system (mimiq.test_flow).

None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.

Its remote endpoint lists its tools without sign-in, and its tools changed 2 times since Anlyon Radar first saw them.

Last scanned Nov 8, 2026, version 0.5.1.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

2 tools

Changes things 1Claude Code: ask
  • 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.Reads text others writeCan send data outNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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 task by clicking, typing and filling in forms (they get a working inbox for verification codes). They report what was broken, what did nothing, where they got stuck or gave up and why, with the step and a screenshot, and the problems ranked by how many agents hit them. Pass the URL and, as goal, the task a user would try in plain words. For a protected preview or pages behind a sign-in, pass access (a Vercel bypass secret, a username and password, or a test account). Each agent keeps going until it finishes the task or gets stuck, so a run takes a few minutes, longer for a long task; each agent uses 5 credits. This call answers within a minute with status still_running, a session_id and a report link while the run goes on: call mimiq.show_report with the session_id until it is finished (if it returns a review, handle that audience warning as below). The same call made again joins that run and uses no more credits. It starts right away and the result includes the audience summary, examples and fit. If the recruited crowd is not the requested audience (more than 1 in 5 wrong) or the page could not be read to check its market, the result is an audience_review instead: show the warning, then continue with review_id, confirm_audience and audience_fit_acknowledged, or recruit again with audience_correction.

    Annotations the server declares

    • title: Test a flow
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • 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…No findings

    Why it is in this group

    • The name "mimiq.show_report" says "show": a word for reading.
    Description, as the server wrote it
    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 credits.

    Annotations the server declares

    • title: Show a Mimiq report
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:12 UTC, unchanged since Oct 29, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
1
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://mcp.mimiqai.com/.well-known/oauth-protected-resource/mcp
Authorization servers
https://mcp.mimiqai.com
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
no
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://mcp.mimiqai.com/mcp: tools/list returned 2 tools to an anonymous client, including mimiq.test_flow (write)

    What this check looks for

Posture changes

  1. Oct 29, 2026
    • Tools that change things, listed without credentials: 8 to 1

Findings

Matches of fixed checks, with the text they matched.

No check matched anything in these tool definitions. That is not a safety guarantee.

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools2 changed.~2 changedView diff
  2. PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 1.View diff
    • Tools that change things, listed without credentials: 8 to 1
  3. Tools7 removed, 2 changed.−7 removed~2 changedView diff
    • Removed:mimiq.ask_audience
    • Removed:mimiq.compare_copy
    • Removed:mimiq.compare_urls
    • Removed:mimiq.test_component
    • Removed:mimiq.test_copy
    • Removed:mimiq.test_page
    • Removed:mimiq.test_text
    • Changed:mimiq.show_reportOnly readsdescription
    • Changed:mimiq.test_flowChanges thingsdescription

Install

Pinned to version 0.5.1. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__mimiq__mimiq_show_report"
    ],
    "ask": [
      "mcp__mimiq__mimiq_test_flow"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as mimiq. Review it before you use it.

Capability tags behind 1 rule
  • mcp__mimiq__mimiq_test_flow untrusted-input, outbound

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.victorgulchenko/mimiq-mcp/verify?hash=765cddc2a75c59e7b86af53ed10f6d7cf0af218ddbe94bfc33c4f9cadfa21246" | jq -e '.changed == false'

Pinned hash 765cddc2a75c, from Nov 8, 2026, 17:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.victorgulchenko/mimiq-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.victorgulchenko/mimiq-mcp
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.victorgulchenko/mimiq-mcp.svg)](https://radar.anlyon.com/servers/io.github.victorgulchenko/mimiq-mcp)

Source: MCP Registry · repository. Synced Oct 22, 2026, 20:17 UTC.

Mimiq: AI agents use your app like your users and find what breaks MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the Mimiq: AI agents use your app like your users and find what breaks MCP server safe?

No scan can promise that. What its definitions show: 2 tools, 1 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the Mimiq: AI agents use your app like your users and find what breaks MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the Mimiq: AI agents use your app like your users and find what breaks MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the Mimiq: AI agents use your app like your users and find what breaks MCP server have?

2 tools: 1 write, 1 read. mimiq.test_flow and mimiq.show_report.

Does the Mimiq: AI agents use your app like your users and find what breaks MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the Mimiq: AI agents use your app like your users and find what breaks MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): mimiq.test_flow.

Has the Mimiq: AI agents use your app like your users and find what breaks MCP server changed its tools?

Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 8, 2026. Every change is on this page and in its Atom feed.