omi
AI that sees your screen, listens to your conversations and tells you what to do
The Omi MCP server provides Model Context Protocol integration for an AI-powered context capture system that records screen activity and conversations. It enables AI assistants to access transcribed memories, conversation summaries, and action items captured by Omi devices and desktop applications. Developers can integrate this server to give their AI agents persistent memory of everything a user has seen or heard, supporting desktop, mobile, and wearable hardware platforms. The server connects to Omi's backend API to retrieve real-time transcriptions, speaker-diarized conversations, and structured summaries.
Key Features
Use Cases
- 01Enable AI assistants to recall details from past meetings and conversations
- 02Build productivity tools that automatically track action items from screen activity
- 03Create personal knowledge management systems with searchable conversation history
- 04Develop AI agents that remember context across multiple work sessions
- 05Integrate wearable-captured audio transcripts into desktop AI workflows
- 06Build custom chat interfaces with access to a user's complete interaction history
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
omi — FAQ
What is the Omi MCP server?+
The Omi MCP server is a Model Context Protocol integration that exposes Omi's conversation transcription, screen capture, and memory APIs to AI assistants. It allows agents to access real-time and historical data from recordings made by Omi desktop apps, mobile apps, and wearable hardware.
How do I install the Omi MCP server?+
Clone the Omi repository and navigate to the mcp/ directory. Configuration details depend on whether you're using the public cloud backend or running the full local Python backend stack with Firebase credentials. The macOS quick start requires Xcode and Node.js; Windows requires Node.js.
Which AI clients work with this MCP server?+
Any client that supports the Model Context Protocol can connect to the Omi MCP server, including Claude Desktop and other MCP-compatible AI assistants.
Do I need API keys to use the Omi MCP server?+
The quick-start mode connects to Omi's public cloud backend without credentials. For local development with the full backend, you'll need to configure Firebase, Deepgram API keys, and optionally Redis and GPU-based services in the .env file.
Is the Omi MCP server free and open source?+
Yes, the entire Omi project including the MCP server is MIT licensed and fully open source. The cloud backend and mobile/desktop apps are available at no cost, with optional hardware devices sold separately.
What platforms does the Omi MCP server support?+
The MCP server integrates with Omi's cross-platform ecosystem: macOS 14+ desktop app (Swift/Python), Windows desktop (Node.js), iOS and Android mobile apps (Flutter), and Bluetooth-connected wearable hardware running nRF/Zephyr firmware.
How do I install omi?+
Open the source repository on GitHub and follow its README. omi is a mcp server — MCP Agents Market links you directly to the official repo.
Is omi free?+
omi is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.