mcptube-vision transforms YouTube videos into a persistent, structured knowledge base using both transcripts and visual frame analysis. Built on the Karpathy LLM Wiki pattern: knowledge compounds…
Mcptube is an MCP project maintained in the 0xchamin/mcptube repository. The maintainer describes its purpose as “mcptube-vision transforms YouTube videos into a persistent, structured knowledge base using both transcripts and visual frame analysis. Built on the Karpathy LLM Wiki pattern: knowledge…”. Read the project documentation for the complete scope.
The project provides a local client configuration using mcptube. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| add_video | Ingest video + build wiki |
| list_videos | List library |
| remove_video | Remove video + clean wiki |
| wiki_list | Browse wiki pages |
| wiki_show | Read a wiki page |
| wiki_search | Full-text search |
| wiki_toc | Table of contents |
| wiki_ask | Agentic Q&A |
| wiki_history | Version history |
| get_frame | Extract frame (inline image) |
| get_frame_by_query | Frame by transcript match |
| classify_video | Get metadata for classification |
| generate_report | Get data for single-video report |
| generate_report_from_query | Get data for cross-video report |
| synthesize | Get data for theme synthesis |
| discover_videos | Search YouTube |
| ask_video | Single-video Q&A data |
| ask_videos | Multi-video Q&A data |
{
"mcpServers": {
"mcptube": {
"command": "mcptube",
"args": [
"serve",
"--stdio"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Store entities, relations and observations in a local knowledge graph with the reference Memory MCP server.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Enables AI assistants to securely interact with Azure DevOps through a standardized protocol.