Video Research MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add -e "GEMINI_API_KEY=${GEMINI_API_KEY}" video-research-mcp -- uvx video-research-mcp
Required:GEMINI_API_KEY
README.md

Gemini 3.1 Pro powered video analysis, research, and content extraction

video-research-mcp

Claude Code can't process video. Gemini 3.1 Pro can. This plugin bridges the two -- giving Claude access to Gemini's video understanding, multi-source research, and web search through MCP.

Watch the full demo on YouTube

What's in the box

A Claude Code plugin -- not just MCP servers, but a full integration: 45 tools, 17 slash commands, 7 skills, and 7 sub-agents that work together out of the box. The MCP servers provide the tools, the commands give you quick workflows (/gr:video, /gr:research), the skills teach Claude how to use everything correctly, and the agents handle background tasks like parallel research and visualization.

Server Tools Purpose
video-research-mcp 33 Video analysis, deep research, content extraction, web search, knowledge store, academic research
video-creation 17 Synthesize explainer videos from research — project setup, pipeline, quality, audio, and parallel scene generation (wraps video_explainer + Claude Agent SDK)

Install

npx video-research-mcp@latest
export GEMINI_API_KEY="your-key-here"

One install. One API key. The installer copies 17 commands, 7 skills, and 7 agents to ~/.claude/ and configures the MCP servers to run via uvx from PyPI.

npx video-research-mcp@latest --check     # show install status
npx video-research-mcp@latest --uninstall  # clean removal
npx video-research-mcp@latest --local      # install for this project only

Requires Python >= 3.11, uv, Node.js >= 16, and a Google AI API key.

What it does

Watch a meeting recording

/gr:video-chat ~/recordings/project-kickoff.mp4
> "Create meeting minutes in Dutch. Screenshot every shared screen."

Gemini watches the full video and pulls out timestamps, decisions, and action items. For local files, ffmpeg extracts frames at key visual moments. Files over 20MB are uploaded to Gemini's File API and context-cached -- follow-up questions reuse the cache instead of re-uploading.

Analyze a YouTube tutorial

/gr:video https://youtube.com/watch?v=...

Same capabilities, applied to YouTube. You get precise timestamps, a concept map, and comment sentiment analyzed in the background.

Research a topic with evidence grading

/gr:research "HNSW index parameters for high-dimensional embeddings"

Runs web search and Gemini analysis in parallel. Every finding gets an evidence tier -- Confirmed, Strong Indicator, Inference, or Speculation -- so you know how much weight to give each claim. Results are visualized as an interactive evidence network.

Analyze papers, URLs, or directories

/gr:analyze https://arxiv.org/abs/2401.12345
/gr:analyze ~/papers/attention-is-all-you-need.pdf
/gr:analyze ~/papers/                              # cross-document comparison

Works with PDFs, URLs, and raw text. Extracts entities, relationships, and key arguments. Point it at a directory and it compares all documents in a single pass. Supports PDF, TXT, MD, HTML, XML, JSON, CSV.

Research grounded in source documents

/gr:research-doc ~/papers/
/gr:research-doc paper1.pdf paper2.pdf "Compare methodologies and find contradictions"

Four-phase pipeline: Document Mapping, Evidence Extraction, Cross-Reference, Synthesis. Every claim is cited back to document and page number. Documents are uploaded once and reused across all phases.

Search the web

/gr:search "latest developments in MCP protocol"

Google Search via Gemini grounding with source citations.

Recall what you've learned

/gr:recall                                # overview: stats + saved analyses
/gr:recall "kubernetes"                   # semantic search + filesystem grep
/gr:recall ask "what do I know about X?"  # AI-powered Q&A with source citations

Nothing gets lost. Every analysis and research finding is stored automatically. Weeks later, in a different project, you just ask. When Weaviate is configured, searches use semantic matching -- find "gradient descent tuning" even when you searched for "ML optimization". Without Weaviate, recall fal

Tools (5)

video_analysisAnalyze video files or YouTube URLs for timestamps, decisions, and action items.
deep_researchPerform web research with evidence grading and synthesis.
document_analysisExtract entities, relationships, and arguments from PDFs, URLs, or directories.
web_searchPerform Google Search with source citations via Gemini grounding.
knowledge_recallRetrieve stored research findings and analyses.

Environment Variables

GEMINI_API_KEYrequiredGoogle AI API key for Gemini 3.1 Pro access

Configuration

claude_desktop_config.json
{"mcpServers": {"video-research-mcp": {"command": "uvx", "args": ["video-research-mcp"]}}}

Try it

/gr:video-chat ~/recordings/project-kickoff.mp4 'Create meeting minutes in Dutch. Screenshot every shared screen.'
/gr:video https://youtube.com/watch?v=example_id
/gr:research 'HNSW index parameters for high-dimensional embeddings'
/gr:analyze ~/papers/attention-is-all-you-need.pdf
/gr:recall ask 'what do I know about kubernetes?'

Frequently Asked Questions

What are the key features of Video Research MCP?

Gemini 3.1 Pro integration for video understanding. Evidence-graded research with source citations. Cross-document comparison and synthesis. Semantic knowledge recall with Weaviate support. Multi-format support including PDF, TXT, MD, HTML, XML, JSON, and CSV.

What can I use Video Research MCP for?

Generating meeting minutes and action items from long video recordings. Analyzing YouTube tutorials to create concept maps and sentiment summaries. Conducting academic research with evidence-tier grading for claims. Comparing methodologies across multiple research papers in a directory. Semantic searching across past research findings and saved analyses.

How do I install Video Research MCP?

Install Video Research MCP by running: npx video-research-mcp@latest

What MCP clients work with Video Research MCP?

Video Research MCP works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep Video Research MCP docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare