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

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

Server Details

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

If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.

Status: Healthy
Uptime: 58.8% over 81 days
Last Tested: 2026-11-06 21:28
Transport: Streamable HTTP · MCP 2025-11-25
URL
Repository: victorgulchenko/mimiq-mcp
GitHub Stars: 1
Server Listing: Mimiq MCP
ChatGPT: –
Claude: –

TDQS

A4.1/5.0

Scored 2026-11-03 11:10 across 2 tools

Disambiguation4/5

The two tools have a clear primary split: mimiq.test_flow starts or joins a test run, while mimiq.show_report reads and polls results. However, test_flow's description embeds audience-review follow-up actions such as confirm_audience and audience_correction without exposing them as distinct tools, creating some boundary ambiguity.

Naming Consistency5/5

Both tools use the same mimiq. prefix and a consistent snake_case verb_noun pattern: show_report and test_flow. There is no mixing of naming conventions.

Tool Count4/5

Two tools is minimal but reasonable for a focused service whose core workflow is starting a test and viewing its report. It is slightly under the typical 3-15 range, but each tool earns its place.

Completeness3/5

The core run-and-report lifecycle is covered, but the surface lacks explicit operations for listing, canceling, or managing runs. Audience-review handling is described inside test_flow rather than exposed as clear follow-up operations, which may leave agents unsure how to proceed.

Available Tools

2 tools

mimiq.show_reportShow a Mimiq reportA

Read-onlyIdempotent

Inspect

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.

Name	Required	Description	Default
`session_id`	Yes
`compare_session_id`	No

Output Schema

Name	Required	Description
`kind`	Yes
`title`	Yes
`reason`	Yes
`review`	No
`status`	No
`credits`	No
`findings`	No
`headline`	Yes
`progress`	No
`versions`	Yes
`limitation`	Yes
`report_url`	Yes

TDQS

A4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the description only needed to add the non-obvious traits — and it does: a blocking wait of up to 40 seconds, account-scoped reads, and zero credit cost. Those are exactly the operational facts an agent cannot infer from the annotations; the absence of any partial-result note on timeout is a minor gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the core action, then the return content, then the inputs and cost/safety note. Every clause carries information an agent would otherwise have to guess.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be spelled out, yet the description still summarizes it usefully. The blocking-wait limit and cost/scope note round out a simple two-parameter read tool; the only real hole is the undocumented compare_session_id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning, and it only half does: session_id is explained as coming from an earlier run, but compare_session_id is never mentioned at all. The "or a report URL" phrasing also conflicts with the session_id pattern ^[A-Za-z0-9_-]{1,100}$, which no URL would satisfy.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Show a saved Mimiq run" pairs a specific verb with a specific resource, and the description enumerates what the output contains (run status, per-agent hits, stop reasons, report link). The only sibling, mimiq.test_flow, is not named, so the differentiation is achieved by implication rather than explicit contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use the session ID from an earlier run" clearly situates the tool after a run has been created, and the waiting behavior tells the agent this can be polled for status. No explicit exclusion or named alternative is given, and the fallback "or a report URL" is never reconciled with the schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

mimiq.test_flowTest a flowAInspect

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.

Name	Required	Description
`url`	Yes	Where the flow starts. Must be publicly reachable. For localhost, open a cloudflared tunnel and pass the tunnel URL.
`goal`	No	The task each person tries, e.g. "complete the signup and reach the dashboard". Default: sign up and start using it.
`count`	No	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.
`access`	No	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 browser prompt. headers: up to 4 headers sent only to this site. login: a test account (email or username, password, optional note) that the people sign in with to reach pages behind a sign-in. Used for this run only and never shown in results or reports. Ask the user before passing a password, and use a test account, not a real one.
`devices`	No	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.
`new_run`	No	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.
`audience`	No	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.
`max_steps`	No	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.
`review_id`	No	The review_id from a low-fit review or completed/running result. Bound to this URL and test kind.
`confirm_audience`	No	Start with the reviewed people after showing them to the user.
`audience_correction`	No	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_acknowledged`	No	Set only after telling the user about an audience-fit warning and they choose to continue.

Output Schema

Name	Required	Description
`run`	No
`call`	No
`tool`	Yes
`status`	No
`report_url`	No
`summary_card`	No

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses cost (5 credits per agent), latency (run takes a few minutes, call answers within a minute with status still_running), the async session_id/report-link contract, and that repeating the call joins the run without extra credits. It also discloses credential handling ('used for this run only and never shown in results or reports') and the audience_review failure mode with its recovery parameters.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger condition and the mental model before the mechanics, and nearly every sentence carries operative content (credits, timing, polling, access, audience review). It is somewhat sprawling as a single dense block, with mild repetition of the still_running/show_report loop and a slightly abrupt 'It starts right away' mid-paragraph, but nothing is truly wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, nested-object, open-world tool with an output schema, the description covers everything an agent needs to call it correctly: triggers, async polling loop, cost model, credential passing, re-run semantics, and the audience_review branch with its recovery path. Return values need not be described because an output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is already 100%, so the baseline is 3; the description adds real meaning by explaining how to phrase goal ('the task a user would try in plain words') and by summarizing the access object's three credential types and when each applies. It leaves devices, max_steps and new_run to the schema, which handles them adequately, so it falls just short of full compensation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource ('AI agents ... open it in their own real browser and try the task by clicking, typing and filling in forms') and precisely what it produces: what was broken, what did nothing, where they got stuck, ranked by how many agents hit each problem. It also names the sibling it hands off to ('call mimiq.show_report with the session_id'), so the agent can tell the two apart without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit when-to-use is given ('after you build or change anything a user goes through ... and again after each fix'), along with the required conditions (preview or staging URL, access for protected pages). Alternatives and follow-ups are spelled out: poll mimiq.show_report until finished, use new_run after a build change, and use review_id plus confirm_audience or audience_correction when the audience is wrong.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

2 tool updatesNov 3, 2026

Changedmimiq.show_report3 fields changed

addedOutput schema / properties / credits

Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

addedOutput schema / properties / findings

Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

addedOutput schema / properties / review

Added value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

Changedmimiq.test_flow2 fields changed

addedInput schema / properties / new_run

Added value: +{
+  "description": "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.",
+  "type": "boolean"
+}

removedInput schema / properties / timeout_seconds

Removed value: -{
-  "default": 1200,
-  "description": "How long to wait for the result. A run still going after this returns still_running with its report link.",
-  "maximum": 3600,
-  "minimum": 60,
-  "type": "integer"
-}

1 tool updateNov 3, 2026

Changedmimiq.show_report1 field changed

addedOutput schema / properties / versions / items / properties / decisions

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "count": {
+        "minimum": 0,
+        "type": "integer"
+      },
+      "label": {
+        "type": "string"
+      },
+      "tone": {
+        "enum": [
+          "good",
+          "bad",
+          ""
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "label",
+      "count",
+      "tone"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

1 tool updateOct 23, 2026

Changedmimiq.test_flow1 field changed

addedInput schema / properties / devices

Added value: +{
+  "description": "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.",
+  "enum": [
+    "mix",
+    "phone",
+    "laptop"
+  ],
+  "type": "string"
+}

1 tool updateOct 23, 2026

Changedmimiq.test_flow4 fields changed

changedInput schema / properties / max_steps / description

Previous value: -"Optional step limit per person (10 to 60). The server defaults to 40."New value: +"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."

changedInput schema / properties / max_steps / maximum
```
Previous value: -60New value: +200
```

addedInput schema / properties / timeout_seconds / description

Added value: +"How long to wait for the result. A run still going after this returns still_running with its report link."

changedInput schema / properties / timeout_seconds / maximum
```
Previous value: -1800New value: +3600
```

7 tool updatesOct 22, 2026
- Removedmimiq.ask_audience
- Removedmimiq.compare_copy
- Removedmimiq.compare_urls
- Removedmimiq.test_component
- Removedmimiq.test_copy
- Removedmimiq.test_page
- Removedmimiq.test_text

1 tool updateOct 21, 2026

Changedmimiq.test_flow1 field changed

addedInput schema / properties / access

Added value: +{
+  "additionalProperties": false,
+  "description": "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 browser prompt. headers: up to 4 headers sent only to this site. login: a test account (email or username, password, optional note) that the people sign in with to reach pages behind a sign-in. Used for this run only and never shown in results or reports. Ask the user before passing a password, and use a test account, not a real one.",
+  "properties": {
+    "basic_auth": {
+      "additionalProperties": false,
+      "properties": {
+        "password": {
+          "maxLength": 256,
+          "type": "string"
+        },
+        "username": {
+          "maxLength": 256,
+          "type": "string"
+        }
+      },
+      "required": [
+        "username",
+        "password"
+      ],
+      "type": "object"
+    },
+    "headers": {
+      "additionalProperties": {
+        "maxLength": 2048,
+        "type": "string"
+      },
+      "type": "object"
+    },
+    "login": {
+      "additionalProperties": false,
+      "properties": {
+        "email": {
+          "maxLength": 320,
+          "type": "string"
+        },
+        "note": {
+          "maxLength": 300,
+          "type": "string"
+        },
+        "password": {
+          "maxLength": 256,
+          "type": "string"
+        }
+      },
+      "required": [
+        "email",
+        "password"
+      ],
+      "type": "object"
+    },
+    "vercel_bypass": {
+      "maxLength": 256,
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

1 tool updateOct 1, 2026

Changedmimiq.show_report1 field changed

addedOutput schema / properties / progress

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "done": {
+      "minimum": 0,
+      "type": "integer"
+    },
+    "total": {
+      "minimum": 1,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "done",
+    "total"
+  ],
+  "type": "object"
+}

1 tool updateSep 30, 2026
- Changedmimiq.show_report2 fields changed
  - addedOutput schema / properties / status
```
Added value: +{
+  "enum": [
+    "finished",
+    "running"
+  ],
+  "type": "string"
+}
```
  - changedOutput schema / properties / versions / minItems
```
Previous value: -1New value: +0
```

1 tool updateSep 30, 2026

Changedmimiq.show_report4 fields changed

addedOutput schema / properties / versions / items / properties / answers

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "option": {
+        "type": "string"
+      },
+      "person": {
+        "type": "string"
+      },
+      "reason": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "person",
+      "option",
+      "reason"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedOutput schema / properties / versions / items / properties / counts / required

Previous value: -[
-  "total",
-  "stayed",
-  "left"
-]New value: +[
+  "total"
+]

addedOutput schema / properties / versions / items / properties / unanswered
```
Added value: +{
+  "minimum": 0,
+  "type": "integer"
+}
```

addedOutput schema / properties / versions / items / properties / votes

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "count": {
+        "minimum": 0,
+        "type": "integer"
+      },
+      "option": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "option",
+      "count"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

2 tool updatesSep 30, 2026

Changedmimiq.test_flow2 fields changed

changedInput schema / properties / audience_correction / description

Previous value: -"Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts at 80% fit or more, otherwise returns a new review."New value: +"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."

changedInput schema / properties / audience_fit_acknowledged / description

Previous value: -"Set only after telling the user about a below-80% fit warning and they choose to continue."New value: +"Set only after telling the user about an audience-fit warning and they choose to continue."

Changedmimiq.test_page2 fields changed

changedInput schema / properties / audience_correction / description

Previous value: -"Not quite? Change who and rerun: use with review_id. Recruits a new crowd under the existing credit rules; starts at 80% fit or more, otherwise returns a new review."New value: +"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."

changedInput schema / properties / audience_fit_acknowledged / description

Previous value: -"Set only after telling the user about a below-80% fit warning and they choose to continue."New value: +"Set only after telling the user about an audience-fit warning and they choose to continue."

9 tool updatesSep 30, 2026

Changedmimiq.ask_audience1 field changed