worthwatch
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GROQ_API_KEY | No | API key for Groq, used when the brain is configured as `api` with Groq. | |
| GEMINI_API_KEY | No | API key for Gemini's API (has a free tier), used when the brain is configured as `api` with Gemini. | |
| OPENAI_API_KEY | No | API key for OpenAI, used when the brain is configured as `api` with OpenAI. | |
| WORTHWATCH_HOME | No | Set this to keep all three folders (config, data, output) in one folder instead of the default locations. | |
| OPENROUTER_API_KEY | No | API key for OpenRouter, used when the brain is configured as `api` with OpenRouter. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| 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. |
| 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. |
| 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. |
| 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. |
| 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. |
| 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. |
| add_ideaC | Put an idea of your own on the idea board. |
| kill_ideaA | Kill an idea on the board, with the reason, so it stops being suggested. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.