A Model Context Protocol server for Omi interaction and automation. This server provides tools to read, search, and manipulate Memories and Conversations.
To use the Omi MCP server, you need an API key. You can generate one in the Omi app under Settings > Developer > MCP
. The API key can be provided with each tool call. If not provided, the server will use the OMI_API_KEY
environment variable as a fallback.
Add this to your claude_desktop_config.json
:
Install docker, https://orbstack.dev/ is great.
Replace your_api_key_here
with the key you generated in the Omi app.
https://github.com/BasedHardware/omi/tree/main/mcp/examples
get_memories
limit
(number, optional): Maximum number of memories to retrieve (default: 100)categories
(array of MemoryFilterOptions, optional): Categories of memories to retrieve (default: [])create_memory
content
(string): Content of the memorycategory
(MemoryFilterOptions): Category of the memorydelete_memory
memory_id
(string): ID of the memory to deleteedit_memory
memory_id
(string): ID of the memory to editcontent
(string): New content for the memoryget_conversations
include_discarded
(boolean, optional): Whether to include discarded conversations (default: false)limit
(number, optional): Maximum number of conversations to retrieve (default: 25)You can use the MCP inspector to debug the server. For uvx installations:
Or if you’ve installed the package in a specific directory or are developing on it:
Running tail -n 20 -f ~/Library/Logs/Claude/mcp-server-omi.log
will show the logs from the server and may
help you debug any issues.
If you are self-hosting the Omi backend, you can specify the API endpoint by setting the OMI_API_BASE_URL
environment variable.
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.