---
title: "tube-bridge"
description: "Self-hosted YouTube research system bundling a 17-tool MCP with timestamped frame extraction, canonical workflow, corpus doctrine, onboarding, and reusable research templates."
canonical: https://agentpluginsdirectory.com/plugins/tube-bridge
last-updated: 2026-09-25
---

# tube-bridge
Self-hosted YouTube research system bundling a 17-tool MCP with timestamped frame extraction, canonical workflow, corpus doctrine, onboarding, and reusable research templates.
- Slug: tube-bridge
- Publisher: TheWhiteWater
- Repository: https://github.com/TheWhiteWater/tube-bridge
- Manifest: plugin.json
- Version: 1.1.6
- License: MIT
- Category (editorial): research
- Skills: 1 (tube-bridge-research)
- MCP servers: 1 (tube-bridge)
- Stars: 0
- Repository created: 2026-08-07
- Repository last pushed: 2026-08-26
- Publisher type: User
- Listing: https://agentpluginsdirectory.com/plugins/tube-bridge
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What tube-bridge does, in the publisher's words

Self-hosted YouTube research for AI agents.

Search videos and channels, read transcripts and comments, extract timestamped frames, and build private semantic-search corpora, through 17 MCP tools.

- 14 of 17 tools need no YouTube API key.
- Local-first corpus: transcripts, vectors, and indexes stay on your machine.
- Useful research output: titles, similarity scores, canonical video URLs, and timestamp links.
- One tool for one frame: return visual evidence near a transcript finding without keeping media files.
- Self-hosted and MIT: no account, hosted intermediary, managed storage, or vendor lock-in.

Thanks to everyone already using tube-bridge. If it saves you time, consider starring the repository, it helps others discover the project and signals that publishing more work like this is worthwhile.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/TheWhiteWater/tube-bridge/HEAD/README.md

## Skills

- tube-bridge-research: Operate tube-bridge as a coherent YouTube research system: frame questions, discover sources, select subtitle tracks, classify claims, test competing hypotheses, capture timestamped evidence, build and search local corpora, and report traceable conclusions. Use for evidence-oriented YouTube researc…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- tube-bridge: transport: stdio; command: python3 -m tube_bridge.cli; env: TUBE_BRIDGE_CACHE

Read from the plugin's own mcp.json. Environment variable names only, never values.