worthwatch
Checks YouTube channels for new videos, reads video transcripts/captions, and provides tools for judging and managing video digests based on user context and rules.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@worthwatch check my followed YouTube channels and show today's digest"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
worthwatch
worthwatch checks the YouTube channels you follow and tells you which new videos are worth your time.
It judges every video against a short file you write about your own projects, so the answer is about you.
What a day looks like
Here is part of one day's digest for Mara Quinn, who sells bookkeeping software to bakeries and writes a newsletter for indie game makers. She and these videos are invented, but the digest is worthwatch's own output (the whole file):
# Digest 2026-03-02
Context file last updated 1 day ago.
- **YES** Ledgerleaf: Email the three bakeries that churned last month and ask which report they missed. [We Got 40 Paying Bakeries Without Ads](https://www.youtube.com/watch?v=SampleVid01)
- **YES** Tidepool: Rewrite the Tidepool welcome email so it links the three most-read issues. [The Welcome Email Every Newsletter Gets Wrong](https://www.youtube.com/watch?v=SampleVid02)
2 kept, 2 read and skipped, 0 read but not written, 1 not read, 0 waiting.
| Verdict | Channel | Title | Reason |
|---|---|---|---|
| YES | Small Software Show | We Got 40 Paying Bakeries Without Ads | |
| YES | Inbox Craft | The Welcome Email Every Newsletter Gets Wrong | |
| MAYBE | Hype Daily | Growth Hacks for 2026 (Number 7 Will Shock You) | |
| MAYBE | Ad Lab | Boost Your Posts: The Paid Ads Playbook | [demoted from YES: it contradicts a standing decision (no paid ads)] |The fourth video was judged YES, then turned into a MAYBE by one of Mara's own rules: she has decided never to pay for ads. worthwatch checks every write-up against rules like that in code, after the model has written it.
Related MCP server: tldw-mcp
Why it exists
I built worthwatch for myself, to keep up with the YouTube channels I follow without watching every video. It reads each new one and tells me which are worth my time for what I'm building right now. I'm giving it away free because anyone exploring a new niche has the same problem, and you don't need a GPU to run it.
What makes it different
It judges for you. Every verdict is about your projects, read from your own context file, not a generic summary.
Your rules are code. Decisions you have made ("no paid ads", "never a free plan") are checked after the model writes. A YES that breaks one becomes a MAYBE, and the digest says why.
No made-up quotes. A quote in a write-up has to match one stretch of the transcript, word for word or within a few words, or it is cut.
Polite to YouTube. Captions first, small daily limits and a gap between requests. When YouTube says stop, worthwatch stops and waits. It never pretends to be a browser, never uses your cookies, and never tries another way in.
Any brain, free ones first. Your own AI agent, a local model, Gemini's free API tier, or the AI tools you already use.
An idea board. Every business idea a video contains, checked and kept in one place.
Made for AI agents. An MCP server and a skill, so Claude Code, Codex, Cursor and others can use it.
No GPU needed.
Quickstart
Install uv, if you do not have it. On macOS or Linux:
curl -LsSf https://astral.sh/uv/install.sh | shOn Windows, in PowerShell:
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"Install worthwatch:
uv tool install git+https://github.com/mokshtheverma-max/worthwatchIf uv warns that its tool folder is not on your PATH, run this once, then open a new terminal so that the
worthwatchcommand is found:uv tool update-shellMake your folders and starter files, and choose the brain that judges the videos:
worthwatch initCheck that everything is ready. It says in plain words what is missing and how to fix it:
worthwatch doctorJudge one video:
worthwatch https://www.youtube.com/watch?v=VIDEO_IDThis needs a brain worthwatch can call (claude, codex, api or ollama). In agent mode, ask your agent instead (see below).
Make it yours: open
context.mdin your config folder and replace the example person with yourself, put the channels you follow inchannels.txt, one link a line, and runworthwatch --channelsonce a day.
Your files live in three folders, which worthwatch init prints:
config (your settings) | data (records and transcripts) | output (digests you read) | |
Windows |
|
|
|
macOS |
| the same folder, |
|
Linux |
|
|
|
Set WORTHWATCH_HOME to keep all three in one folder instead.
Pick your brain
worthwatch init asks; worthwatch init --brain NAME changes it later. Free ones first:
Brain | What it costs you | Setup |
| Nothing extra: worthwatch calls no model, and your own AI agent does the judging | Connect your agent (next section) |
| Nothing: the model runs on your computer | Install Ollama, then |
| Gemini's API has a free tier: Google's pricing page says "Start building free of charge with generous limits" (ai.google.dev/gemini-api/docs/pricing) | Put your key in |
| Uses the Claude Code plan you already have ( | Install Claude Code |
| Uses the Codex plan you already have ( | Install the Codex CLI |
| That service's own prices | Put the key in |
You can also give the quick jobs (sorting a listing, a first look at a transcript) to a different
brain from the write-ups, for example a free local model for the quick jobs and claude to write:
set quick = "ollama" under [brain] in settings.toml.
Use it from your AI agent
worthwatch mcp is an MCP server with eight tools: check your channels for new videos, read a
transcript, hand your agent everything it needs to judge a video, save the verdict after your
rules have checked it, show today's digest, and list, add or kill ideas.
In Claude Code, one line installs the plugin (the MCP server and a skill that teaches Claude to use it), on Claude Code 2.1.275 or later:
/plugin install worthwatch --marketplace mokshtheverma-max/worthwatchOr add only the server:
claude mcp add worthwatch -- worthwatch mcpFor Claude Desktop, Codex CLI, Cursor and others, see docs/agents.md, which also says which setups were tested.
Privacy
Your context file, channels, transcripts, records and digests stay in your folders, on your computer.
What leaves your computer: requests to YouTube, to read channel listings and captions; and the transcript and your context file, to the brain you chose. With Ollama they stay on your computer; with claude, codex or an API they go to that company; in agent mode they go to your agent.
Jev, an optional paid screen for business ideas, is off unless you switch it on, and is only ever sent public video text, never your context file.
There are no accounts and no telemetry. API keys come from your environment, and worthwatch never writes them to a file.
Responsible use
worthwatch reads public videos for your own use. Respect YouTube's Terms of Service and the people who made the videos.
It reads captions. It can also download a video's audio and transcribe it, but downloading may break YouTube's terms, so that is off unless you switch it on (
[transcripts] audio = true, and the whisper extra:uv tool install --reinstall "worthwatch[whisper] @ git+https://github.com/mokshtheverma-max/worthwatch").Its limits are polite and on by default. If YouTube refuses, it waits and says so; there is no setting to get around a refusal, on purpose.
Do not republish transcripts or write-ups as your own work.
Troubleshooting
Something is not working: run
worthwatch doctor. Every line that needs fixing says how."YouTube refused the request for now (HTTP 429)": your network is being told to slow down. Wait;
worthwatch statusshows when the next try is."Your brain is agent mode": worthwatch calls no model in agent mode. Ask your agent, or run
worthwatch init --brain claude(or codex, api, ollama).A video has no captions: it cannot be read without the audio path (see Responsible use).
"JavaScript runtime" in the doctor: reinstall worthwatch, which brings Deno with it:
uv tool install --reinstall git+https://github.com/mokshtheverma-max/worthwatch.Claude Desktop cannot find
worthwatch: use the full path;uv tool dir --binprints the folder it is in.
More
Settings:
settings.tomlandrules.tomlin your config folder, made byworthwatch init, explain themselves line by line. The example person's files are in src/worthwatch/examples.License: Apache-2.0.
Available Tools
8 toolsadd_ideaC
Put an idea of your own on the idea board.
Inputs: idea (required), why_now, how_much, who_pays, +1 more.
check_channelsA
List new videos from the channels in your channels.txt, priority channels first. It fetches no transcript and calls no model. Each channel listed is one polite YouTube request, so at most max_channels are listed per call; call again to go on through the rest.
Inputs: days, max_channels.
get_transcriptA
The transcript of one YouTube video (a video link or its 11-character id): from this machine if worthwatch already has it, otherwise from YouTube's captions, politely. A refusal means wait.
Inputs: video (required).
judge_videoB
Everything an agent needs to judge one video for the user: step 1, the rules that decide the verdict (YES, OPPORTUNITY, MAYBE or NO) with the user's context; step 2, the write-up's exact format with the full transcript; step 3, how to save it. worthwatch calls no model here: you do the judging.
Inputs: video (required).
kill_ideaA
Kill an idea on the board, with the reason, so it stops being suggested.
Inputs: reason (required), idea_id (required).
list_ideasA
The idea board: every idea worthwatch has found in the videos or you added, with who pays, how much, a first step and how many videos back it. Killed ideas only when asked for.
Inputs: include_killed.
save_verdictB
Store your verdict and write-up for one video. worthwatch first checks them against the user's own rules in code, exactly as it checks a model's: quotes must be in the transcript, a YES needs a live project and an action, and nothing may break a standing decision. The verdict that comes back is the one the digest will show.
Inputs: video (required), verdict (required), write_up (required).
todays_digestA
The digest of one day (today unless day is given as YYYY-MM-DD): every video read that day, its verdict, and the day's ideas.
Inputs: day.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct stage or resource: channel polling, transcript retrieval, judging guidance, verdict persistence, daily digest, and idea-board CRUD. Although judge_video includes transcript context, its purpose is clearly separated from get_transcript by the judging rules and output format.
Most tools follow a predictable verb_noun or verb_object pattern: check_channels, get_transcript, judge_video, save_verdict, list_ideas, add_idea, kill_idea. todays_digest is the main deviation, but the set remains easy to read and understand.
Eight tools is well scoped for a YouTube monitoring, judging, and idea-tracking workflow. Each tool covers a meaningful operation without apparent redundancy.
The surface covers the core lifecycle: discover videos, fetch transcripts, judge, save verdicts, review digests, and manage ideas. Minor gaps exist around channel configuration or verdict revision, but agents can likely work around them through the file-backed channels.txt and repeated saves.
Maintenance
Related MCP Connectors
An MCP server that gives any LLM or agent clean YouTube transcripts on demand: a single video, a whole channel, or a playlist, plus AI cleanup of auto-generated captions. API-key auth, credit-based, same backend as the public v1 API. Get a free API key with 25 free credits at youtubetranscriptdownload.com/account.
Hosted YouTube MCP server for Claude, ChatGPT and Cursor, with each action switched per account.
MCP server for generating rough-draft project plans from natural-language prompts.
An MCP server that gives your AI access to the source code and docs of all public github repos
Related MCP Servers
- AlicenseBqualityDmaintenanceAn MCP server designed to fetch transcripts for YouTube videos. It enables AI tools to access video text content for tasks like summarization, analysis, and key takeaway extraction.174MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that extracts YouTube video transcripts (including metadata) as Markdown, enabling AI to summarize and discuss video content without watching it.MIT
- AlicenseNot gradedqualityDmaintenanceAn MCP server that turns your AI assistant into a structured ideation partner by generating, scoring, critiquing, and storing software ideas locally with a built-in web dashboard.7 npm1PolyForm Noncommercial 1.0.0
- AlicenseAqualityDmaintenanceMCP server that lets AI agents search YouTube and fetch transcripts.23MIT