Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Authorization not required, issuer https://mcp.mimiqai.com
Authorization not required, issuer https://mcp.mimiqai.com
Changed the definition of "mimiq.test_flow"
⟨132 unchanged words⟩ and password, or a test account).AEach agent keeps going until it finishes the task or gets stuck, so a run takes a fewminutes;minutes, longer for a long task; each agent uses 5 credits. It starts right ⟨58 unchanged words⟩
⟨308 unchanged words⟩ "minimum":1,"type":"integer"},"devices":{"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"},"goal":{"description":"The task each person ⟨21 unchanged words⟩ :"string"},"max_steps":{"description":"OptionalUsuallystepleavelimitthisperout:personeach
Removed "mimiq.ask_audience", "mimiq.compare_copy", "mimiq.compare_urls" and 4 more; changed the definition of "mimiq.show_report" and "mimiq.test_flow" (9 tools before, 2 now)
Show the finished result of a saved Mimiqtest, or two saved tests comparedrun: what thecall,agentscountshit,objectionswhereineachsimulatedstoppedpeople'sandwordswhy, and afull
Changed the definition of "mimiq.test_flow"
⟨51 unchanged words⟩ the task a customer would try as goal. For a protected preview or pages behind a sign-in, pass access (a Vercel bypass secret, a username and password, or a test account). A run takes a few minutes and each ⟨79 unchanged words⟩
{"properties":{"access":{"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"},"Certificate changed, valid to 2027-01-15
Authorization not required, issuer https://mcp.mimiqai.com
Changed the definition of "mimiq.ask_audience", "mimiq.test_component", "mimiq.test_copy" and 3 more
AskUse this to ask simulated people a multiple-choice question (2 to ⟨26 unchanged words⟩
ShowUse this after you build or change a UI component (a button, card, form, modal, navigation or pricing table)to: simulated peopleand hearsay
Authorization not required, issuer https://mcp.mimiqai.com
Authorization not required, issuer https://mcp.mimiqai.com
Changed the definition of "mimiq.test_flow" and "mimiq.test_page"
⟨9 unchanged words⟩ than 1 in 5 not the requested audience);or the page could not be read to check its market; the result includes the audience summary, examples and fit. Onlya wrong crowdthosereturnsreturn audience_review: show the warning, then use review_id ⟨56 unchanged words⟩
⟨9 unchanged words⟩ Authorization not required, issuer https://mcp.mimiqai.com
Authorization not required, issuer https://mcp.mimiqai.com
Authorization not required, issuer https://mcp.mimiqai.com
Authorization not required, issuer https://mcp.mimiqai.com
Authorization not required, issuer https://mcp.mimiqai.com
Changed the definition of "mimiq.show_report"
⟨9 unchanged words⟩ ,"limitation":{"type":"string"},"progress":{"additionalProperties":false,"properties":{"done":{"minimum":0,"type":"integer"},"total":{"minimum":1,"type":"integer"}},"required":["done","total"],"type":"object"},"reason":{"type":"string"},"report_url":{"format":"uri","type":"string"},"status":{"enum":["finished","running"],"type":"string"},"title":{"type":"string"},"versions" ⟨135 unchanged words⟩ :"object"},"maxItems":2,"minItems":10,"type":"array"}},"required":[ ⟨9 unchanged words⟩
Certificate recorded, valid to 2026-12-21
Authorization not required, issuer https://mcp.mimiqai.com
Added "mimiq.show_report"; changed the definition of "mimiq.ask_audience", "mimiq.compare_copy", "mimiq.compare_urls" and 5 more (8 tools before, 9 now)
before
—after
Ask an audiencebefore
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":false,"readOnlyHint":Changed the definition of "mimiq.test_flow" and "mimiq.test_page"
Starts immediately at 80% audience fit or more and includes audience summary, examples and fit in the result. Only below 80% returns audience_review: show the warning, then use review_id, confirm_audience and audience_fit_acknowledged to continue, or audience_correction to recruit again. Send simulated people through a multi-step flow (signup ⟨38 unchanged words⟩
⟨36 unchanged words⟩ "maxLength":500,"type":"string"},"audience_correction":{"description":"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.","maxLength":1500,"type":"string"},"audience_fit_acknowledged":{"description":"Set only after telling the user about a below-80% fit warning and they choose to continue.","type":"boolean"},"confirm_audience":{"description":"Start with the reviewed people after showing them to the user.","type":"boolean"},"count":{"default":5,"description":"How ⟨64 unchanged words⟩ ,"type":"string"},"max_steps":{"
Changed the definition of "mimiq.test_flow"
Only numbers and dates differ: this server embeds live figures in the definition, so the text moves without the contract changing.
⟨28 unchanged words⟩ Slower than test_page, and each person uses305 credits. Returns each person's steps, where they stopped and why.
⟨67 unchanged words⟩ Each runs a full browser session and uses305 credits.","maximum":10,"minimum":1, ⟨87 unchanged words⟩
Unavailable → Live
First tool surface recorded: 8 tools (server version 0.4.0)
Showing the latest 24 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Use thisbeforeafter youshipbuild or change anything a user goes through (signup, onboarding, checkout,orsettings,otheramulti-stepnewchangefeature), on the preview or staging URL, and again after each fix.SimulatedAIpeopleagents,goeachthroughacting as one of theflowapp's users, open it inatheir own real browser,clickingandtypingtry the task by clicking, typing and filling in forms (they get a working inbox for verification codes). They reportthewhatstepwas broken, what did nothing, where they got stuck or gave up and why, with the step andwhy.aPassscreenshot, and thepreviewproblemsorrankedstagingby how many agents hit them. Pass the URL,and, as goal, the task acustomeruser would tryasingoal.plain words. For a protected preview or pages behind a ⟨13 unchanged words⟩ test account). A run takes a fewminutes andminutes; eachpersonagent uses 5 credits.Returns each person's steps, where they stopped and why, and the problems they hit.It starts right away and the result includes ⟨53 unchanged words⟩
Ask an audience — Use this to ask simulated people a multiple-choice question (2 to 10 options) and get each person's pick and reasoning. Use it for naming, positioning, or which feature to build next. Each person answers on their own.
Compare two versions of copy — Compare two versions of copy or an email on the same simulated people and get Mimiq's call on which to ship. The same people see version A and version B. Mimiq's call combines a forecast of how people like them behave, asked in both orders, with how the same people moved: clear, leaning, or too close to call (no pick). Returns the call, the reason in one sentence, how many people moved toward each version, each version's top objections, and a link to the report. Without a key, an agent also gets one free A/B test on up to 10 simulated people per version, while the daily free A/B allowance las…
Compare two pages — Compare two web pages (for example a preview deployment and production) on the same simulated people and get Mimiq's call on which to ship. The same people see page A and page B. Mimiq's call combines a forecast, asked in both orders, with how the same people moved: clear, leaning, or too close to call (no pick). Returns the call, the reason in one sentence, how many people moved toward each page, each page's top objections, and a link to the report. Needs public URLs. Without a key, an agent also gets one free A/B test on up to 10 simulated people per version, while the daily free A/B allowa…
Test a UI component — Use this after you build or change a UI component (a button, card, form, modal, navigation or pricing table): simulated people say whether they understand it, trust it and would use it. Provide component_html, component_text, or both. With a key, the result ends with a link to the full report in the Mimiq app.
Test copy — Use this when you write or change a headline, tagline, value proposition, email subject line or call to action: simulated people read it and say how they react and why. To choose between two versions, use mimiq.compare_copy. This tool still accepts variant_b and then runs that same comparison. Returns each person's reaction, objections and what would help, and the counts. With a key, the result ends with a link to the full report in the Mimiq app.
Test a page — Use this after you build or change a landing, pricing or signup page, then fix what people raised and test it again. Simulated people look at the page, scroll it and say what confused them, what they doubted and what would change their mind. They do not click: to see whether people can get through a signup or checkout, use mimiq.test_flow. Needs a public URL (for localhost, open a tunnel first; see the server instructions). Returns each person's action, thoughts and objections, and the counts. With a key, the result ends with a link to the full report in the Mimiq app. It starts right away an…
Test text — Use this when you write or change other text a customer will read (a positioning statement, feature description, error message, instructions or an announcement): simulated people read it and say how they react. Pass goal to say what the text should achieve. Returns each person's reaction, objections and what would help. With a key, the result ends with a link to the full report in the Mimiq app.
ShowUseonethispiecewhenofyoucopywrite(or change a headline, tagline, value proposition, email subject line or call to action) to: simulated people read it andhearsay how they react and why. To choose between ⟨44 unchanged words⟩
StartsUseimmediatelythisunlessbeforetheyourecruitedshipcrowdaissignup,wrongonboarding,(morecheckoutthanor1otherinmulti-step5change,notandtheagainrequestedafteraudience)eachorfix. Simulated people go through thepageflowcouldinnotaberealreadbrowser,toclickingcheckanditstyping,market;and report theresultstepincludeswherethetheyaudiencegotsummary,stuckexamplesor gave up, andfit.why.OnlyPassthosethereturnpreviewaudience_review:orshowstaging URL, and thewarning,taskthenausecustomerreview_id,wouldconfirm_audiencetryandasaudience_fit_acknowledgedgoal.toAcontinue,runortakesaudience_correctionatofewrecruitminutesagain.andSendeachsimulatedpersonpeopleusesthrough5acredits.multi-stepReturnsfloweach(signup,person'sonboardingsteps,checkout)whereintheyastoppedrealandbrowserwhy,clickingand the problems they hit. It starts right away andtypingthe result includes the audience summary,toexamplesfindand fit. If thesteprecruitedwherecrowdtheyisgetnotstuckthe requested audience (more than 1 in 5 wrong) orgivetheup.pageSlowercouldthannottest_page,beandreadeachtopersoncheckusesits5market,credits.theReturnsresulteachisperson'sanstepsaudience_review instead: show the warning,wherethentheycontinuestoppedwith review_id, confirm_audience andwhy.audience_fit_acknowledged, or recruit again with audience_correction.
Starts immediately unless the recruited crowd is wrong (more than 1 in 5Usenotthistheafterrequestedyouaudience)build orthe page could not be read to check its market; the result includes thechangeaudienceasummarylanding,examples and fit. Only those return audience_review:pricingshoworthesignupwarningpage, thenuse review_id, confirm_audience and audience_fit_acknowledgedfixtowhatcontinue,peopleorraisedaudience_correctionandtotestrecruitit again.Show a web page to simulatedSimulated peopleand hear how they react: who would stay,lookwhoatwouldtheleavepage,and why. Each person scrolls thescrollpageit andsayssay what confused them, what they doubted and what would change their mind.Use it after you buildTheyordochangenotaclick:landing,topricingseeorwhethersignuppeoplepage,canthengetfixthroughwhatatheysignupraisedorandcheckout,testuseagain.mimiq.test_flow. Needs a public URL (for localhost, open ⟨27 unchanged words⟩ to the full report in the Mimiq app. 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.
ShowUseanythis when you write or change other text a customer will read (a positioning statement, feature description, error message, instructions or an announcement)to: simulated people read it andhearsay how they react. Pass goal to say what ⟨30 unchanged words⟩
before
—after
Compare two versions of copybefore
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":false,"readOnlyHint":truefalse,"title":"Compare two versions of copy"}
before
—after
Compare two pagesbefore
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":truefalse,"title":"Compare two pages"}
before
—after
Test a UI componentbefore
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":false,"readOnlyHint":truefalse,"title":"Test a UI component"}
before
—after
Test copybefore
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":false,"readOnlyHint":truefalse,"title":"Test copy"}
before
—after
Test a flowStarts immediatelyatunless80%theaudiencerecruitedfitcrowdoris wrong (moreandthan 1 in 5 not the requested audience); the result includes the audience summary, examples andfit in the result.fit. Onlybelowa80%wrong crowd returns audience_review: show the warning, then use ⟨57 unchanged words⟩
⟨53 unchanged words⟩ new crowd under the existing credit rules; startsatunless80%thefitneworcrowdmoreis wrong, otherwise returns a new review.","maxLength" ⟨5 unchanged words⟩ :"Set only after telling the user abouta below-80%anfitaudience-fit warning and they choose to continue.","type ⟨171 unchanged words⟩
before
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}before
—after
Test a pageStarts immediatelyatunless80%theaudiencerecruitedfitcrowdoris wrong (moreandthan 1 in 5 not the requested audience); the result includes the audience summary, examples andfit in the result.fit. Onlybelowa80%wrong crowd returns audience_review: show the warning, then use ⟨113 unchanged words⟩
⟨53 unchanged words⟩ new crowd under the existing credit rules; startsatunless80%thefitneworcrowdmoreis wrong, otherwise returns a new review.","maxLength" ⟨5 unchanged words⟩ :"Set only after telling the user abouta below-80%anfitaudience-fit warning and they choose to continue.","type ⟨124 unchanged words⟩
before
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":truefalse,"title":"Test a page"}
before
—after
Test textbefore
—after
{"additionalProperties":true,"properties":{"call":{"additionalProperties":true,"properties":{"headline":{"type":"string"},"pick":{"type":["string","null"]},"reason":{"type":"string"}},"type":"object"},"report_url":{"type":["string","null"]},"run":{"additionalProperties":true,"type":"object"},"status":{"type":"string"},"summary_card":{"type":"string"},"tool":{"type":"string"}},"required":["tool"],"type":"object"}{"destructiveHint":false,"idempotentHint":false,"openWorldHint":false,"readOnlyHint":truefalse,"title":"Test text"}
Show a Mimiq report — Show the finished result of a saved Mimiq test, or two saved tests compared: the call, counts, objections in simulated people's words, and a full report link. Use session IDs from an earlier test result or report URL. Reads your account only and spends no credits.
Starts immediately at 80% audience fit or more and includes audience summary, examples and fit in the result. Only below 80% returns audience_review: show the warning, then use review_id, confirm_audience and audience_fit_acknowledged to continue, or audience_correction to recruit again. Show a web page to simulated people and ⟨94 unchanged words⟩
⟨36 unchanged words⟩ "maxLength":500,"type":"string"},"audience_correction":{"description":"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.","maxLength":1500,"type":"string"},"audience_fit_acknowledged":{"description":"Set only after telling the user about a below-80% fit warning and they choose to continue.","type":"boolean"},"confirm_audience":{"description":"Start with the reviewed people after showing them to the user.","type":"boolean"},"count":{"default":10,"description":"How ⟨32 unchanged words⟩ up for the waitlist\".","maxLength":500,"type":"string"},"review_id":{"description":"The review_id from a low-fit review or completed/running result. Bound to this URL and test kind.","maxLength":100,"type":"string"},"timeout_seconds":{" ⟨39 unchanged words⟩