Video Research
Give Claude Code 51 research, analysis & media production tools with one command. Video analysis, deep research, academic papers, TTS voice-over, AI video generation, and Weaviate knowledge store — powered by Gemini 3.5 Flash.
What is Video Research?
Video Research is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to give claude code 51 research, analysis & media production tools with one command. video analysis, deep research, academic papers, tts voice-over, ai video generation, and weaviate knowledge store — po...
Give Claude Code 51 research, analysis & media production tools with one command. Video analysis, deep research, academic papers, TTS voice-over, AI video generation, and Weaviate knowledge store — powered by Gemini 3.5 Flash.
This server falls under the Data Science & ML and Search & Data Extraction categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Give Claude Code 51 research, analysis & media production to
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx video-researchConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Video Research
The video-research MCP server gives Claude Code a suite of 51 research and media production tools powered by Google's Gemini model, enabling deep video analysis, academic paper research, web content extraction, text-to-speech voice-over generation, AI video production pipelines, and a persistent Weaviate knowledge store for semantic recall across sessions. It is organized into three sub-servers — video-research-mcp (34 tools), video-explainer-mcp (15 tools), and video-agent-mcp (2 tools) — and connects to multiple external services including Google AI, ElevenLabs, OpenAI Sora, YouTube, Weaviate, and Cohere. Researchers, content creators, and analysts use it to automate the full pipeline from raw video or academic papers through to narrated, produced video explainers.
Prerequisites
- Python 3.11 or later
- uv package manager installed (curl -LsSf https://astral.sh/uv/install.sh | sh)
- Node.js 16 or later (for the npx installer)
- A Google AI (Gemini) API key — required (GEMINI_API_KEY)
- Optional: ElevenLabs API key for TTS, OpenAI API key for Sora video, Weaviate instance URL and API key for knowledge store, YouTube Data API key
Run the installer
The npx installer handles Python dependency setup via uv and registers the MCP servers. Run it once to install and verify the setup.
npx video-research-mcp@latest
# Verify installation
npx video-research-mcp@latest --checkSet required environment variables
At minimum, export your Gemini API key. Add optional keys for additional capabilities like TTS, Sora video, or the Weaviate knowledge store.
export GEMINI_API_KEY="your-google-ai-api-key"
export ELEVENLABS_API_KEY="your-elevenlabs-key" # optional: TTS voice-over
export OPENAI_API_KEY="your-openai-key" # optional: Sora AI video
export WEAVIATE_URL="http://localhost:8080" # optional: knowledge store
export WEAVIATE_API_KEY="your-weaviate-key" # optional
export YOUTUBE_API_KEY="your-youtube-key" # optional: YouTube metadataAdd the server to Claude Desktop config
Add video-research-mcp to your Claude Desktop configuration using uvx, which will resolve and run the installed package.
{
"mcpServers": {
"video-research": {
"command": "uvx",
"args": ["video-research-mcp"],
"env": {
"GEMINI_API_KEY": "your-google-ai-api-key"
}
}
}
}Restart Claude Desktop or Claude Code
Reload your MCP client so the new server is picked up. With 51 tools available, the server may take a few seconds to initialize on first use.
Test with a simple research query
Ask Claude to perform a quick web research task to confirm the tools are active and Gemini is responding correctly.
Video Research Examples
Client configuration
Claude Desktop configuration using uvx to run the video-research-mcp server with Gemini and optional ElevenLabs keys.
{
"mcpServers": {
"video-research": {
"command": "uvx",
"args": ["video-research-mcp"],
"env": {
"GEMINI_API_KEY": "your-google-ai-api-key",
"ELEVENLABS_API_KEY": "your-elevenlabs-api-key",
"WEAVIATE_URL": "http://localhost:8080",
"WEAVIATE_API_KEY": "your-weaviate-api-key"
}
}
}
}Prompts to try
Example prompts that exercise video analysis, deep research, academic paper lookup, and knowledge store recall.
- "Analyze this video file and create timestamped minutes with key discussion points: /recordings/meeting.mp4"
- "Do deep research on HNSW index parameter tuning and give me a summary with evidence grading"
- "Search for recent academic papers on retrieval-augmented generation and compare their methodologies"
- "Generate a voice-over script for a 3-minute explainer on transformer attention mechanisms and produce the audio"
- "Search my knowledge store for everything I've previously researched about Kubernetes autoscaling"Troubleshooting Video Research
Installation fails with Python version or uv not found errors
Install uv first with 'curl -LsSf https://astral.sh/uv/install.sh | sh' and confirm Python 3.11+ is available. Run 'npx video-research-mcp@latest --check' to diagnose missing dependencies.
GEMINI_API_KEY not set or Gemini API returns authentication errors
The Gemini API key is the only required credential and must be in the env block of your MCP config. Obtain a key from Google AI Studio (aistudio.google.com) and ensure the Gemini API is enabled for your project.
TTS or video generation tools return errors or are not available
Voice-over generation requires ELEVENLABS_API_KEY and AI video generation requires OPENAI_API_KEY. These capabilities are disabled if the corresponding keys are absent. Add the relevant keys to your env block to enable them.
Frequently Asked Questions about Video Research
What is Video Research?
Video Research is a Model Context Protocol (MCP) server that give claude code 51 research, analysis & media production tools with one command. video analysis, deep research, academic papers, tts voice-over, ai video generation, and weaviate knowledge store — powered by gemini 3.5 flash. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Video Research?
Follow the installation instructions on the Video Research GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Video Research?
Video Research works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Video Research free to use?
Yes, Video Research is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Video Research Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Video Research? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Video Research in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Video Research?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.