Pixeltable
A multimodal mcp server
What is Pixeltable?
Pixeltable is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to multimodal mcp server
A multimodal mcp server
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A multimodal mcp server
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx pixeltableConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Pixeltable
The Pixeltable MCP Server is a multimodal data processing server that exposes audio, video, image, and document capabilities to AI assistants through the Model Context Protocol. It runs four specialized index services covering audio transcription and semantic search, video frame extraction and content search, image object detection and similarity search, and document text extraction with RAG support. Teams building multimodal pipelines can use it to let Claude or other MCP clients query, index, and retrieve rich media data without writing custom integration code.
Prerequisites
- Docker and Docker Compose installed (recommended deployment method)
- Python 3.10+ and pip if running locally
- pixeltable Python package (pip install pixeltable)
- An MCP-compatible client such as Claude Desktop or Claude Code
- Sufficient disk space for media indexing data
Clone the MCP server repository
Clone the pixeltable-mcp-server repository from GitHub.
git clone https://github.com/pixeltable/pixeltable-mcp-server.git
cd pixeltable-mcp-server/serversInstall the pixeltable Python package
Install the core pixeltable library which the server depends on.
pip install pixeltableStart all four index servers with Docker Compose
Use Docker Compose to build and launch the audio (8080), video (8081), image (8082), and document (8083) servers in one command.
docker-compose up --buildVerify services are running
Check that all four services are available on their designated ports.
curl http://localhost:8080/health # audio
curl http://localhost:8081/health # video
curl http://localhost:8082/health # image
curl http://localhost:8083/health # documentConfigure your MCP client
Add each service endpoint to your MCP client configuration to expose the multimodal tools to your AI assistant.
Pixeltable Examples
Client configuration
Claude Desktop configuration pointing at the Pixeltable MCP server running via Docker Compose.
{
"mcpServers": {
"pixeltable-audio": {
"command": "docker",
"args": ["run", "--rm", "-i", "-p", "8080:8080", "pixeltable-mcp-server-audio"]
},
"pixeltable-document": {
"command": "docker",
"args": ["run", "--rm", "-i", "-p", "8083:8083", "pixeltable-mcp-server-document"]
}
}
}Prompts to try
Example prompts after connecting the Pixeltable MCP server to your AI assistant.
- "Transcribe the audio file at /data/interview.mp3 and search for mentions of budget"
- "Extract frames from the video and find the timestamps where a person is on screen"
- "Find all images in the collection that look similar to this product photo"
- "Extract text from the PDF report and answer: what were the Q3 revenue figures?"Troubleshooting Pixeltable
Docker Compose build fails with missing dependencies
Ensure Docker Desktop is running and you have an active internet connection for pulling base images. Run docker-compose down then docker-compose up --build to force a clean rebuild.
Port conflicts when starting the servers
One of ports 8080-8083 may be in use. Stop other services on those ports or edit the docker-compose.yml port mappings to use different host ports.
Media indexing is slow or times out
Large media files require significant processing time. Increase the Docker memory allocation in Docker Desktop settings and ensure your machine has at least 8 GB RAM available for the containers.
Frequently Asked Questions about Pixeltable
What is Pixeltable?
Pixeltable is a Model Context Protocol (MCP) server that multimodal mcp server It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Pixeltable?
Follow the installation instructions on the Pixeltable GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Pixeltable?
Pixeltable works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Pixeltable free to use?
Yes, Pixeltable is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Pixeltable Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Pixeltable? 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 Pixeltable 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 Pixeltable?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.