MCP App Store
by KeenEthics
FRIDAI icon

FRIDAI MCP Server for ChatGPT

By FansNetwork Inc.

Overview

Connect your FRIDAI account to inspect and improve the AI reply Notebooks for the brands and services you own or manage with full sharing permissions. The built-in Notebook Optimizer loads its current workflow from FRIDAI, helps identify conflicting rules and missing business facts, proposes targeted changes, and supports version history and synthetic Chat reply previews. Authorized users can apply reviewed Notebook or reply-setting changes. Message Center tools provide scoped conversation reading and export; they do not send, edit, or delete customer messages. FRIDAI Post tools manage content drafts and schedules where the connected service and explicit permissions allow them. Sign in with FRIDAI and choose the brand and service to work on. An eligible FRIDAI service and the relevant permissions are required. Reply previews may use your configured model provider; unsupported or unavailable features are reported explicitly.

How to connect

  1. ChatGPT: Open the FRIDAI listing in the ChatGPT app directory and choose Connect. ChatGPT listing FRIDAI exposes 72 tools here.

Tools

analyze_notebook_quality

ChatGPT
Returns passed/total structural check counts, issues, concisenessCheck and replyQuality.status=not_tested with score=null. Long ordinary candidates are checked against a 15,000 to 20,000-character target; over-target length and long repeated instructions are flagged for compaction even below the 50,000-character storage limit, and shorter complete Notebooks are not flagged for being short. It never proves semantic equivalence, overall AI quality or publication readiness. Takes an eligible subscriptionId for its latest Notebook, or content for a candidate. No model is called and nothing is saved.

analyze_rule_structure

ChatGPT
Legacy basic text structure check; no reply model is called, quality remains untested, and it gives no AI quality score.

attach_onboarding_notebook_draft

ChatGPT
Writes the saved onboarding Notebook draft (and its business info) into the Notebook of a brand this login owns, usually the one just bought. The first call previews the current Notebook and the draft and returns a confirmationToken; the second call with confirm: true saves it. Any existing text is backed up as a version first.

cancel_scheduled_posts

ChatGPT
Cancels 1–30 scheduled or failed posts so they are not published, the same as deleting them in the dashboard. Published posts are not touched. Preview first, then confirm with the returned token.

check_account_connections

ChatGPT
For 檢查我的帳號連線, 為什麼一直要重新授權, 授權過期, Token 過期, 權限不足, 授權失敗, IG 授權沒成功. Checks every Facebook Page, Instagram, Threads, LINE official account and X account of a brand live with the platform (not the stored status), says in plain words why an authorization stopped working (password changed, security check, access removed, Page role, Instagram not a professional account, LINE token reissued), separates real problems from false alarms and from errors reauthorizing cannot fix, and returns FRIDAI's own reauthorization link with the steps. Leave subscriptionId out to check every brand of this login. Read-only.

check_duplicate_replies

ChatGPT
重複回覆檢查 (為什麼客人收到兩次回覆, 檢查有沒有別的自動回覆, Meta AI / LINE 關鍵字自動回應 / 歡迎訊息 answering too). For each LINE, Facebook and Instagram private-message account it reads what the platform lets FRIDAI read (LINE response mode and webhook, apps installed on the Page, the FRIDAI welcome message and LINE native-reply list) and the conversation history (Page replies sent by an automation or another app next to a FRIDAI reply, the same Page text sent to several customers, replies Meta refused because another app controls the conversation, LINE menu texts FRIDAI answered). Returns findings (conflict / check / ok), turnOff steps checked on the help pages of each platform, keepLineMenuKeywords (which LINE menu keywords can stay and which conflict) and userMessage. Read-only: nothing on LINE, Meta or FRIDAI changes.

check_reference_accounts

ChatGPT
Reads the latest public posts of up to 10 candidate accounts (Threads, Instagram, Facebook, X, TikTok, YouTube) and returns, for each, whether it exists and is active, its last post date, average likes and three sample posts, plus the accounts already added and the free places per platform (up to 10 per platform). Also returns findingGuide: how to find candidates by web search. Find candidates yourself first; never invent usernames. Nothing is saved.

check_shopify_connection

ChatGPT
Reads the brand's Shopify connection back from Shopify: whether a store is connected, its name, whether the app still has its three read-only scopes and can confirm buyers by email or phone, and in plain words what to fix when it cannot. Read-only.

compare_notebook_rewrite

ChatGPT
Read-only. Compares the current Notebook with a rewritten candidate and blocks silent loss of URLs, emails, phone numbers, money, dates, times, quantities, or exact full-width-quoted phrases. It also blocks unsupported new high-risk facts, formula formatting, numbered cross-references, and unbalanced quotes. Returns a separate concisenessCheck with source/candidate character counts, reduction, section counts and long exact instruction repetitions. Removals and additions passed to it are treated as already verified. A fidelity pass does not by itself show that compaction or optimization is complete.

create_autopost_draft

ChatGPT
Saves the user's own text, optionally with an image or video already in the account's media library, for a date and time. By default it is a draft that is never published until approved in the dashboard; with autoPublish: true it is scheduled and published automatically at that time once the user confirms the preview. Preview first, then confirm with the returned token.

create_autopost_media_upload

ChatGPT
For AI clients that can run commands on the user's computer: returns a 10-minute HTTP PUT upload link for one local file and the mediaUrl it gets once registered in the media library.

create_rule_proposal

ChatGPT
Stores the exact candidate as a reviewable and reproducible test artifact. It does not change production or require the user to visit Dashboard.

explain_missing_reply

ChatGPT
為什麼沒回、怎麼沒回、AI 沒回覆、客人說沒收到回覆、剛剛那則留言怎麼沒回: finds the customer's message and explains in plain words why the AI did not answer it, checking in order whether it reached FRIDAI, whether the AI, a person or the platform's own auto-reply answered, and the recorded reason (AI switched off, paused after a person took over and when it resumes, quiet hours, quota used up, authorization expired, LINE group not @-mentioned, skip settings, a reply held for review, the Notebook handing it to a person). Give the customer name, a piece of the message, or neither for the latest unanswered message. Returns userMessage.zh for the owner and the fixes that apply, each with the exact arguments its fix takes. Read-only.

generate_autopost_text_draft

ChatGPT
Writes text only, in the account's saved voice: a post draft for its platform (saved as a draft awaiting approval, never published automatically) or a spoken short-video script returned as text. For a script, pass structure (one of eight spoken-script structures) so it follows every part in order; length is short, standard (default, about 600 Chinese characters) or long; audience, takeaway and callToAction sharpen it; recent news is checked first unless checkRecentNews is false. Uses the normal AutoPost quota. Preview first, then confirm with the returned token.

get_ads_audit

ChatGPT
廣告健檢 for a brand's Meta ad account (哪支廣告要換, 廣告為什麼變貴, 檢查我的廣告). Read-only, free, no Ads plan needed. Compares the last 14 days with the 14 before and the last 30, judges each running ad by what really happened in FRIDAI (DM leads and their 有效商機 labels; seminar attendance for FRIDAI's own ads) rather than Meta's conversion count, and returns a one-sentence conclusion, a verdict per ad (keep, watch, replace, not delivered, on but not spending, too new, wait) with the reason, five account checks (fair testing, learning, audience, tracking, funnel), a test budget and 3-4 recommendations.

get_ads_coach

ChatGPT
For anyone asking about ads (廣告, 下廣告, 投廣告, 加熱貼文, 預算, 成效分析, 相似受眾, 對手廣告, Ad Library), including owners who have never run an ad. Read-only, free, no Ads plan needed. Returns the brand's Meta ad accounts, Ads plan and ads so far; a nine-stage coaching path (why ads → setup → which post → budget → audience → competitor research → create → analyse → improve); a test budget worked out from monthlyBudget or dailyBudget; a Meta Ad Library link for competitor; lookalike audience steps; and the analysis protocol and decision rules to analyse the results for the user.

get_ai_review_feedback

ChatGPT
Read-only. The AI replies the owner marked 要改 (needs a change) on their own AI 回覆審查 page, newest first: what the owner would have answered (ownerReply), why (ownerNote), the conversation up to the reply they pointed at (customer words de-identified), where it is fixed (Notebook or patrol reply rules) and how to test it. Unhandled ones only unless includeResolved.

get_ai_rule_bundle

ChatGPT
Returns the latest effective notebook, SHA-256 digest, linked-rule state, business information, and safe reply settings for diagnosis.

get_autopost_performance

ChatGPT
Returns the dashboard analytics: totals, recent post metrics, best posting times, content insights and the format and topic ranking compared with the account's usual post.

get_autopost_settings

ChatGPT
Summarizes the AutoPost settings as shown in the dashboard: on/off, writing modes, persona, topic sources, Stories, first comment, hashtags, collaborators, smart optimization, cross-platform sync, weekly times and timezone.

get_autopost_setup_progress

ChatGPT
Shows which of the four AutoPost setup steps are done, the next step, and a dashboard link to it.

get_chat_export_guide

ChatGPT
Step-by-step guide for a shop owner to download the chats they had with customers before FRIDAI was connected (匯出聊天記錄, 匯出聊天紀錄, 下載聊天記錄, 備份聊天記錄, 以前的對話, 舊對話, export chat history) from a LINE Official Account, Instagram, a Facebook Page or their own LINE. One step per call in plain words, with each platform's honest limit (some only allow copying chats one by one) and how the downloaded file becomes Notebook text and keyword replies. FRIDAI itself cannot read chats from before a channel was connected. Read-only; contains no customer data.

get_customer_billing

ChatGPT
Owner-only billing read with mcp:billing:read. Returns saved subscription status, and current Stripe status and up to 20 invoices when this subscription is billed through Stripe. Other providers are explicitly labelled unverified rather than inferred. Cannot cancel, downgrade or refund; no unrestricted billing portal link is returned.

get_customer_invoices

ChatGPT
發票查詢與下載(我要發票、上個月的發票在哪、發票打統編了嗎). Lists every Taiwan payment of this login with its e-invoice: number, date, amount, item name, buyer (統編/抬頭 or personal carrier), status, a 光貿 lookup link, and a PDF link (valid 10 minutes) for 統編 invoices. Each invoice is checked against 光貿, the invoice platform. Payments without an automatic invoice (街口支付, or before 2026-11-03) say so, and what later invoices will be issued to is included. All times are Taiwan time. Read-only. Requires mcp:billing:read.

get_customer_usage

ChatGPT
Reads the selected owned/full-manager subscription usage, monthly quota, bonuses, purchased balance and reset time. Uses the same quota display calculations, including instructor/course pools and keyword-reply units. Read-only database snapshot: no Stripe refresh, trial repair, quota mutation or AI switch change. Requires mcp:insights:read.

get_fridai_connection_status

ChatGPT
Read-only one-call connection check. Returns the authenticated FRIDAI email, eligible brand count and whether the current built-in optimizer is available. Requires no package download, activation or token. Does not audit or change a Notebook and does not prove model compliance or Notebook quality.

get_fridai_product_knowledge

ChatGPT
Returns the current FRIDAI product, feature, navigation, setup, troubleshooting, registration, and evidence-boundary guide. It contains no customer data and does not provide current billing or subscription state.

get_human_notification_destinations

ChatGPT
Lists where each account of a subscription sends 真人通知 (human-takeover alerts) on LINE: every bound LINE group with its name, the personal LINE that verified the owner email, and the shop's own notification bot.

get_keyword_replies

ChatGPT
Reads the keyword auto-replies (關鍵字自動回覆 / 私訊關鍵字回覆) of every account in a subscription: whether they are on, each keyword with its fixed replies, the random delay, and the sha256 needed to change them. The replies are sent as saved, without AI.

get_message_center_conversation

ChatGPT
Returns one authorized conversation with read-only delivery diagnostics: exact inbound-event generation decisions, checkpoint reasons and current pause state when the physical account is unambiguous. Current pause state is not proof of a historical cause; completed generation is not a delivery receipt. It cannot send, edit, delete, retry, or publish messages.

get_notebook_change_outcome

ChatGPT
Compares message counts and human-handoff counts for 7 days before and after one Notebook change (use the versionId from the write result undo field). Counters only, no message text and no quality score; it says when it is too early to conclude.

get_notebook_evidence

ChatGPT
Read-only. For one owned or full-shared subscription, returns whether the AI switch is on, why recent customer messages were skipped, whether human-handoff notifications reached LINE/Telegram, the questions the AI handed to a person together with what the person answered, owner replies that correct or apologise for the AI, what the owner personally tells customers, repeated auto-reply texts, and de-identified customer message topics. Phone numbers, emails, street addresses, ID numbers, filled-in contact fields, account handles, customer names and customer links are masked unless the same value already appears in the brand Notebook.

get_notebook_multiturn_test_plan

ChatGPT
Builds a plan only: no replies are generated or graded. readyToRun means all structural checks passed, not that tests passed. Reply quality remains not_tested with score=null. Covers context carryover, facts, conflicting premises, human handoff and safety.

get_notebook_optimization_protocol

ChatGPT
Read-only. Returns the built-in FRIDAI 優化大師 (Notebook Optimizer) workflow. No package download, local Skill, activation or optimizerRunToken is required. It covers the current three-pass analysis, shortest-equivalent Notebook compaction with a 15,000 to 20,000-character target, fact-ledger, rewrite-fidelity, contradiction-resolution, structural audit, and same-scenario two-round behavioural comparison workflow. Short complete Notebooks stay short; all facts, conditions and fixed payloads are preserved.

get_notebook_optimizer_skill

ChatGPT
Optional legacy FRIDAI 優化大師 Skill package download, activation and receipt verification for clients that use a local adapter. The optimizer is built into this server and works without any download, executable, local Skill or token. A legacy receipt proves package freshness, not model compliance or quality.

get_notebook_version

ChatGPT
Returns one manageable Notebook version so it can be reviewed or restored.

get_reply_edit_patterns

ChatGPT
Returns recent pairs of the AI draft and the reply a person actually sent instead (edited in review, or answered by hand in the IG/FB app). Only the two reply texts are returned, with no customer message, id or name.

get_rule_proposal

ChatGPT
Reads an owned proposal’s status and staleness. Publishing authorization comes from the current MCP write scopes, not a per-proposal Dashboard grant.

get_ruleops_capabilities

ChatGPT
Returns the complete allowlisted persistent Notebook and Reply Settings catalog, including scopes, ranges, and platform restrictions.

get_temporary_announcements

ChatGPT
Lists the temporary announcements of a brand (現在有哪些臨時公告; 臨時公告 such as 公休, 特價到某天, 場地維修暫停, 備用密碼) with their Taiwan-time start and end and state: active (the AI answers with it now), upcoming, or expired (never shown to the AI; listed for 14 days). Also returns nowTaipei, the id of each announcement, and which ones end within 24 hours.

import_autopost_media

ChatGPT
Copies up to 10 public image or video links (JPEG/PNG/WebP up to 15 MB, MP4/MOV up to 100 MB; public Google Drive and Dropbox share links work) into this workspace's FRIDAI media library and returns the library URL of each, ready to use in scheduled posts. Also registers a file uploaded through the upload link from this connector. Adding media publishes nothing, so it needs no confirmation.

list_autopost_accounts

ChatGPT
Lists the AutoPost workspaces this login owns or manages: brand, connected posting accounts and whether auto-posting is on.

list_autopost_media

ChatGPT
Lists the images (or videos) in this workspace's FRIDAI media library, newest first, with the URL a draft or scheduled post can use as its image or video. Up to 20 per page.

list_autopost_posts

ChatGPT
Lists upcoming or recent posts with status, platform, time, a short caption preview (up to 200 characters) and the public link once published. Up to 20 per page.

list_message_center_conversations

ChatGPT
Read-only list of Message Center conversations for brands owned by this login email or shared to it with full-manager access.

list_notebook_versions

ChatGPT
Lists version metadata for an owned Notebook without returning customer conversations or credentials.

list_rule_accounts

ChatGPT
Lists active RuleOps subscriptions owned by this login email or shared to it with the full-manager role. No access tokens or conversations are returned.

list_rule_proposals

ChatGPT
Lists recent proposals for this key owner, including review and publication status. Rotating a key does not hide prior proposals.

list_scheduled_posts

ChatGPT
Lists the workspace's scheduled multi-platform posts — the same ones as the dashboard content calendar: date and time, platforms, a short caption preview (up to 200 characters), per-platform result with the public link once published, and whether each can still be changed or cancelled. Up to 20 per page.

patch_notebook_content

ChatGPT
Inserts, replaces or appends passages in owned Notebook text and leaves every other character unchanged. Each anchor is existing Notebook text that must match exactly and appear only once. The SHA-256 must match the latest content, and the previous content is always saved as a version first.

prepare_message_center_export

ChatGPT
Creates a five-minute CSV download for owned and full-shared brands only. The download rechecks current access.

prepare_rule_reply_test

ChatGPT
Returns the owned pending proposal’s baseline, candidate, synthetic scenario blueprints, and scoring rubric. Your Claude/Codex performs generation and judging with its own quota. FRIDAI calls no model, reads no conversations, stores no test text, and permits no side effects.

preview_comment_replies

ChatGPT
Tests how the current Notebook and an unpublished candidate would answer 1–10 synthetic public comments on a Social (comments) account, through the same reply decision the live comment flow uses: account keyword replies, skip list, #fridai_ mute, smart skip, 略過負評, generation, human handoff and the final safety checks. Each comment takes text, an optional commenter name, the post caption/context and an optional parent (a reply to the account's own reply or to another fan). Per comment and variant it returns the public reply or the outcome code for no reply (for example keyword_reply, skip_friends, ai_no_reply, human_notified_no_public_reply, generated_output_blocked), whether a person would be notified, and privateDm: on Instagram/Facebook a caption with #Fridai tests the comment-to-DM route when the account also has a messages plan. accountGates lists the settings applied to both variants (AI on/off, manual review, reply probability, quiet hours). Requires read and propose scopes, exact current baseSha256 and an owned/full-shared active comments account. No proposal, Notebook save, posted comment, DM, notification, comment history, reply claim, subscription quota or business-state change. Model-provider usage and operational telemetry are expected. Uses synthetic comments only, never real ones; no automatic quality score.

preview_notebook_replies

ChatGPT
Runs one fresh synthetic conversation (1–3 customer turns) against both the current Notebook and an unpublished candidate using the shared FRIDAI DM preview engine. Includes typed humanNotification evidence per turn: would_notify, not_requested, disabled, suppressed, failed or unavailable; wouldNotify=null means incomplete, not a failed Notebook. Notification text can be previewed but actual delivery is never claimed. Requires read and propose scopes, exact current baseSha256 and an owned/full-shared active account. No proposal, Notebook save, provider send, live customer history, subscription quota or business-state mutation. Model-provider usage and operational telemetry are expected. Generation failures include a stage, bounded code and next action; no claimed pass score. Chat only; it takes synthetic customer turns, not real conversations. Both variants use identical account settings and separate synthetic histories. The server reads physical notification identity from the selected account; clients never invent it.

publish_rule_proposal

ChatGPT
Publishes the exact non-stale proposal when the current MCP connection has every required write scope. No per-proposal Dashboard grant is required. Ownership, current state and automatic backup are revalidated atomically.

rate_notebook_change

ChatGPT
Stores the customer's own rating (good or bad) of a Notebook change made through MCP, with optional fixed tags. No free text and no conversations are stored. Ask the customer first; never rate on their behalf.

report_issue_to_fridai

ChatGPT
Sends FRIDAI staff a problem the owner cannot fix in the Notebook or settings: the AI did not reply, sent the same reply twice, still ignores a Notebook rule after the change was saved and tested, replied from the wrong account, or a notification or button did nothing. Include the customer's words, what should happen, what happened and what you tested. Linked feedbackIds are marked handled. At most 5 reports per brand a day; the same problem twice in a day is one report.

resolve_ai_review_feedback

ChatGPT
Marks AI replies the owner marked 要改 as handled, so neither the owner nor FRIDAI staff see them again. resolution notebook is accepted only when the Notebook was saved after the owner marked them; settings is for patrol reply rules or reply settings; no_change needs a reason (the AI reply was already right). A system problem is reported to FRIDAI instead.

restore_notebook_version

ChatGPT
Restores one owned Notebook version after confirming the latest SHA-256. The current text is backed up before restoration.

review_autopost_content

ChatGPT
Starts a content checkup: returns the recent published posts in full (5–30, default 20) with their numbers, each ranked top, middle or bottom against the other posts of the same platform, plain facts about each text, the dashboard insights and best posting times, the upcoming posts that can still be changed, and the fixed steps, checklist, rules and report format to follow. Read-only; nothing is changed.

run_daily_notebook_patrol

ChatGPT
Daily Notebook patrol (每日巡查, 巡查對話, 看看筆記本要不要改). For each brand with AI private-message replies, or the one given, returns the window of the past day, the step-by-step review of every customer conversation in it and the report format: answers that were wrong or outdated, questions the Notebook cannot answer, and staff replies the Notebook should learn from. Read-only: it changes no Notebook, setting or conversation and sends nothing; proposed changes wait for the owner.

schedule_posts

ChatGPT
Schedules 1–30 posts at once, like the dashboard composer: each post has a date and time, the platforms (Instagram, Facebook, Threads, X, LinkedIn, YouTube), shared text, optional media from the media library (image, 2–10 image carousel or video), hashtags, a first comment, a video cover, an Instagram Trial Reel option, 留言領取 (commentToDm: people who comment a keyword get a public reply and a private message; Instagram, Facebook, Threads), and per-platform text, media or account. The first call checks every post and returns one preview of the whole batch plus a confirmationToken (or the problems to fix); a second call with confirm: true and the token saves all posts together, and each is published automatically at its time. TikTok is scheduled in the dashboard.

set_autopost_active

ChatGPT
Pauses or resumes auto-posting. Resuming checks Instagram publishing authorization first, like the dashboard switch. Preview first, then confirm with the returned token.

start_notebook_optimizer

ChatGPT
Start here when the user asks 優化大師, 優化筆記本, 檢查筆記本, 筆記本健檢 or Notebook Optimizer. With empty arguments, loads the current built-in workflow and this login's eligible brands together. Selects the only eligible subscription; asks which brand when several match. Read-only startup, not a completed audit. No local Skill, package, activation, token or user-pasted diagnostic commands are needed.

suggest_autopost_video_topics

ChatGPT
Proposes five short-video topics drawn from the account's AI rules (notebook), after checking the last 7 days of news for its field. Each topic comes with the script structure, audience, takeaway and call to action that fit it, ready to use as the brief for a spoken short-video script. Nothing is saved or published and the posting quota is not used.

unbind_human_notification_destination

ChatGPT
Stops 真人通知 for one account at one destination, like 解除 on the dashboard 真人通知 page. kind group removes that LINE group (groupId) from the account, personal stops the personal LINE messages, custom_bot turns off the shop's own notification bot. Comments that need review still reach the review page and account authorization is not touched. Undoing it needs the customer to bind again in LINE. Without confirm it returns a preview and changes nothing; confirm: true applies it.

update_autopost_settings

ChatGPT
Changes AutoPost settings a customer can change in the dashboard. The first call only previews the before → after change and returns a confirmationToken; a second call with confirm: true and that token saves it. It does not turn auto-posting on or off.

update_keyword_replies

ChatGPT
Saves the keyword auto-replies (關鍵字自動回覆 / 私訊關鍵字回覆) of one account: switch them on or off, replace the keyword rules, or set the random delay before a reply. rules replaces every editable rule of the account, so include the rules to keep; rules managed by FRIDAI (editable: false) are kept automatically. baseSha256 is the sha256 last read for that account, and a stale one is refused. The previous values are returned so the change can be undone.

update_notebook_content

ChatGPT
Directly replaces owned Notebook text only after the supplied SHA-256 matches the latest content. The previous content is always saved as a version first.

update_notebook_settings

ChatGPT
Directly updates AI active state, structured business information, or an owned Notebook link. Touched previous values are saved and stale-checked before the atomic update.

update_reply_settings

ChatGPT
Directly applies allowlisted account and subscription Reply Settings. Touched previous values are saved, ownership is revalidated, and stale or duplicate writes fail closed.

update_scheduled_post

ChatGPT
Changes the date, time, text, platforms, media, hashtags, first comment, 留言領取 (commentToDm) or per-platform content of a post that is not published yet; a failed post given a new time is scheduled again. Preview first, then confirm with the returned token.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/fridai"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/fridai)