Klyf
Klyf is an AI YouTube analyst for creators.
Community: Submitted by a user or imported; check the owner before granting accessDegradedNo sign-inGlobalFreeRead-only
What it can do
- Audit Channel: Give the signed-in user a full audit and overview of THEIR OWN YouTube channel in one answer: the overall state right now, what is working and why, which single thing is constraining th
- Diagnose Channel: Diagnose the signed-in user's YouTube channel.
- Evaluate Idea: Judge whether a specific YouTube video idea, topic, or title the user is weighing up is worth making, grounded in what already converts on their own YouTube channel and what their audie
What data it sees
Do you need an account
No: the server works without sign-in
Klyf is an AI YouTube analyst for creators. Connect your own channel and ask in plain language: why did my last video flop, what should I fix, who is actually watching, what should I make next. Klyf reads your real YouTube analytics, audience data and comments, and answers with a decision instead of another dashboard.
How to connect
How to connect Klyf to Claude
The server address to paste into Claude settings:
https://klyf-mcp.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Klyf to ChatGPT
The server address to paste into ChatGPT settings:
https://klyf-mcp.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Klyf to Cursor
The server address to paste into Cursor settings:
https://klyf-mcp.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (21)
Raw names from tools/list. Only developers need these.
| audit_channel | Give the signed-in user a full audit and overview of THEIR OWN YouTube channel in one answer: the overall state right now, what is working and why, which single thing is constraining the channel (whether people are not being SHOWN the videos or are being shown and not clicking), and what their audience wants. |
| diagnose_channel | Diagnose the signed-in user's YouTube channel. |
| evaluate_idea | Judge whether a specific YouTube video idea, topic, or title the user is weighing up is worth making, grounded in what already converts on their own YouTube channel and what their audience asks for, with a light title/thumbnail direction. |
| suggest_ideas | Generate specific video ideas for the signed-in user's own YouTube channel to make next, grounded in what already earns them subscribers there (their winners) and what their audience keeps asking for (their comments). |
| find_best_videos | Find the signed-in user's best-performing YouTube videos on their own channel, ranked several ways: which produced the most subscribers, the most views, held viewers longest (retention), earned the most total watch time, got clicked most often when shown, and which sparked the most comments, with their titles, so the pattern behind what works becomes clear. |
| find_best_thumbnails | Read what the signed-in user's BEST-performing YouTube thumbnails on their own channel have in common (the on-thumbnail text, faces, colors, layout), to reveal the pattern behind their proven packaging. |
| package_video | Help the signed-in user PACKAGE a YouTube video: generate several title options and thumbnail text ideas, or score a title/thumbnail they already have, always as a title+thumbnail UNIT (making sure the two complement and do not just repeat each other), grounded in the packaging that already converts on their own YouTube channel. |
| draft_description | Draft a YouTube video DESCRIPTION for the signed-in user, in their own voice and structure (learned from the descriptions they already write). |
| draft_script | Draft a video SCRIPT for the signed-in user, in their own voice, built from what already converts on their own YouTube channel and engineered to fix the opening where they lose viewers. |
| review_upcoming_video | Review a YouTube video the signed-in user is ABOUT to publish on their own channel (a scheduled, unlisted, or private/draft upload of theirs, NOT one already public) and give them a prioritized punch-list of what to fix before it goes live: title and thumbnail versus what works on their channel, the description, key settings, and the best time to publish (from when their own uploads have done best and where their audience is). |
| analyze_video | Deep dive on ONE specific YouTube video of the signed-in user's own channel, to explain how it did and why. |
| check_growth | Whether the signed-in user's own YouTube channel is growing, sliding, or flat, and roughly when it turned, from recent views, watch time, and net subscribers. |
| get_weekly_digest | Klyf Pro. |
| analyze_audience | Analyze WHO the signed-in user's YouTube audience is, from their own channel's real data: age and gender of viewers, top countries and where viewers are, and what that means for their content. |
| read_comments | Read and summarize the audience's YouTube comments for the signed-in user's channel: the themes viewers keep raising or asking for, what the audience wants, needs, struggles with, or their pain points and problems (as voiced in comments), and how many comments are unanswered. |
| check_discoverability | Diagnose how the signed-in user's own YouTube channel gets FOUND, and whether new people are finding it at all. |
| enable_auto_reply | Start turning on auto-reply (Klyf posting the YouTube comment replies the user approves on their own channel). |
| read_comment_thread | Read the full reply thread under one YouTube comment on the signed-in user's channel: the original plus the whole back-and-forth, so you can reply in context. |
| reply_to_comment | Post a reply to one specific YouTube comment on the signed-in user's channel, on their behalf. |
| upgrade_to_pro | Give the signed-in user a link to upgrade to Klyf Pro. |
| submit_feedback | Send feedback, a bug report, or a feature request to the Klyf team. |