Skip to main content
Glama
Omi Memories MCP Server

Omi Memories MCP Server

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

  1. Install dependencies:

npm install
  1. Configure your user ID:

    • Open src/server.ts

    • Update the SPECIFIC_USER_ID constant with your user ID from the Account section of the Omira App

  2. Build the TypeScript code:

npm run build
  1. Start the server:

npm start

Available 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:

  1. The Express API to be running at http://localhost:3000

  2. The user ID should configured : Update the SPECIFIC_USER_ID constant in src/server.ts to 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:

  1. Open Cursor IDE settings

  2. Navigate to "AI & Copilot" settings

  3. 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 tool
fetch-memoriesD

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    D1.8/5.0

    Scored across 1 tool

    Disambiguation5/5

    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.

    Naming Consistency5/5

    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.

    Tool Count2/5

    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.

    Completeness2/5

    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.

    Related MCP Connectors

    Related MCP Servers