Memos Api MCP

🚀 MCP Server for MemOS API

This is a Model Context Protocol (MCP) implementation for the MemOS API service. It offers a command - line interface to interact with the MemOS API following MCP standards.

🚀 Quick Start

MCP Configuration

To use this package in the MCP Client, apply the following configuration:

{
  "mcpServers": {
    "memos-api-mcp": {
      "command": "npx",
      "args": ["-y", "@memtensor/memos-api-mcp"],
      "env": {
        "MEMOS_API_KEY": "your-api-key",
        "MEMOS_USER_ID": "your-user-id",
        "MEMOS_CHANNEL": "the-site-where-you-are-seeing-this-document"
      }
    }
  }
}

Configuration Explanation

• command: Utilizes npx to run the package.
• args: Arguments provided to npx for running the package.
• env: Environment variables.
  • MEMOS_API_KEY: Your Memos API key for authentication. (Get your API Key in Dashboard [https://memos-dashboard-pre.openmem.net/cn/quickstart/])
  • MEMOS_USER_ID: A stable per - human identifier. It must be deterministic and non - PII, and should remain the same for the same person across devices/sessions. Never reuse it across different people. Do not use random values, device IDs, or model/chat session IDs. Recommended: SHA - 256(lowercase(trim(email))) or your SSO subject/employee ID.
  • MEMOS_CHANNEL: The site where you are viewing this document. Candidate values: MODELSCOPE, MCPSO, MCPMARKETCN, MCPMARKETCOM, GLAMA, PULSEMCP, MCPSERVERS, LOBEHUB, MEMOS (meaning the MemOS official website), GITHUB (meaning this README file).

Available MCP Tools

This package offers the following MCP tools:

1. add_message

   • Adds a new message to a conversation.
   • Parameters:
     • conversation_id: The conversation ID to identify the conversation the message belongs to.
     • messages: An array of messages containing role and content information.
       • role: The role of the message sender, e.g., user, assistant.
       • content: The message content.

2. search_memory

   • Searches for memories in a conversation.
   • Parameters:
     • query: The search query to find relevant content in the conversation history.
     • conversation_id: The conversation ID to define the search scope.
     • memory_limit_number: The maximum number of results to return, with a default of 6.

3. get_message

   • Retrieves messages from a conversation.
   • Parameters:
     • conversation_id: The conversation ID to identify which conversation's messages to retrieve.

All tools use the same configuration and require the MEMOS_API_KEY environment variable.

✨ Features

• An MCP - compliant API interface.
• A command - line tool for easy interaction.
• Built with TypeScript for type safety.
• An Express.js server implementation.
• Zod schema validation.

📦 Installation

You can install the package globally using either npm or pnpm:

Using npm

npm install -g @memtensor/memos-api-mcp

Using pnpm

pnpm add -g @memtensor/memos-api-mcp

💻 Usage Examples

Basic Usage

After installation, you can run the CLI tool in the following ways:

Using npx

npx @memtensor/memos-api-mcp

If installed globally

memos-api-mcp

🔧 Technical Details

Development

1. Clone the repository:

git clone <repository-url>
cd memos-api-mcp

2. Install dependencies:

pnpm install

3. Start the development server:

pnpm dev

4. Build the project:

pnpm build

Available Scripts

• pnpm build: Build the project.
• pnpm dev: Start the development server using tsx.
• pnpm start: Run the built version.
• pnpm inspect: Inspect the MCP implementation using @modelcontextprotocol/inspector.

Project Structure

memos-mcp/
├── src/           # Source code
├── build/         # Compiled JavaScript files
├── package.json   # Project configuration
└── tsconfig.json  # TypeScript configuration

Dependencies

• @modelcontextprotocol/sdk: ^1.0.0
• express: ^4.19.2
• zod: ^3.23.8
• ts-md5: ^2.0.0

Version

Current version: 1.0.0 - beta.2