Omi Memories MCP Server
The Omi Memories MCP Server enables users to access and interact with their Omi memories through a tool interface.
Fetch Memories: Retrieve all memories associated with a specific user ID from the OMI App via the
fetch-memoriestoolIntegration: Works with MCP-compatible applications like Claude Desktop and Cursor IDE
Configuration: Requires a pre-configured user ID in the server code (
src/server.ts) and runs alongside an Express API athttp://localhost:3000
Connects to an Express API running locally to fetch memory data for the configured user
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Omi Memories MCP Serverfetch my recent memories"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Omi Memories MCP Server
This is a Model Context Protocol (MCP) server that provides access to Omi memories for a specific user through a tool interface.
Features
Tool to fetch all memories for the specified user ID from the OMI App
Related MCP server: MCP-Mem0
Setup
Install dependencies:
npm installConfigure your user ID:
Open
src/server.tsUpdate the
SPECIFIC_USER_IDconstant with your user ID from the Account section of the Omira App
Build the TypeScript code:
npm run buildStart the server:
npm startAvailable Tools
fetch-memories
Fetches all memories for the configured user ID.
import { Client } from "@modelcontextprotocol/sdk/client/index.js";
import { StdioClientTransport } from "@modelcontextprotocol/sdk/client/stdio.js";
const transport = new StdioClientTransport({
command: "node",
args: ["dist/server.js"]
});
const client = new Client(
{
name: "example-client",
version: "1.0.0"
},
{
capabilities: {
tools: {}
}
}
);
await client.connect(transport);
// Fetch memories using the tool
const result = await client.callTool({
name: "fetch-memories",
arguments: {}
});
console.log(result.content[0].text);Configuration
The server expects:
The Express API to be running at
http://localhost:3000The user ID should configured : Update the
SPECIFIC_USER_IDconstant insrc/server.tsto your user ID which you could get from the Account section of the Omira App.
Claude Desktop Integration
To integrate with Claude Desktop, update your Claude Desktop configuration (claude_desktop_config.json) to include:
{
"mcpServers": {
"omi-mcp": {
"command": "node",
"args": [
"/path/to/your/mcp-server/dist/server.js"
],
"env": {
"NODE_ENV": "development"
}
}
}
} Cursor IDE Integration
To integrate with Cursor IDE:
Open Cursor IDE settings
Navigate to "AI & Copilot" settings
Under "Model Context Protocol", add a new MCP server with these settings:
{
"name": "Omi Memories",
"command": "node",
"args": [
"/path/to/your/mcp-server/dist/server.js"
],
"cwd": "/path/to/your/mcp-server",
"env": {
"NODE_ENV": "development"
}
}Replace /path/to/your/mcp-server with the actual path to your MCP server installation directory.
Available Tools
1 toolfetch-memoriesD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v1.0.0- Changed
fetch-memories1 field changed- removed
Input schema / additionalPropertiesRemoved value: -false
1 tool update
- First observed
fetch-memories
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'fetch-memories' stands alone with a distinct purpose, making disambiguation trivial.
The single tool name 'fetch-memories' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.
A single tool is too few for a server named 'Omi Memories MCP Server', which suggests a domain involving memory storage or retrieval. This minimal set likely leaves significant functionality uncovered, making it inappropriate for the implied scope.
Inferred from the server name and tool name, the domain involves memories, but with only a fetch operation, there are obvious gaps such as creating, updating, deleting, or searching memories. This severely incomplete surface will cause agent failures in handling memory lifecycles.
Maintenance
Related MCP Connectors
Model Context Protocol server for Studex tools, notifications, and profile integrations
Cross-tool persistent memory and context for AI assistants over MCP.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
An MCP memory server. One memory your agents share — across models, devices and apps.
Related MCP Servers
- FlicenseBqualityDmaintenanceA Model Context Protocol server that enables AI assistants to interact with the Omi API for retrieving and creating conversations and memories for users.44-
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides AI agents with persistent memory capabilities through Mem0, allowing them to store, retrieve, and semantically search memories.684MIT
- AlicenseNot gradedqualityDmaintenanceA server that implements the Model Context Protocol, providing a standardized way to connect AI models to different data sources and tools.3 npm11MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that provides knowledge graph-based persistent memory for LLMs, allowing them to store, retrieve, and reason about information across multiple conversations and sessions.9104,795 npm2MIT