MemOS API

Provides an MCP-compliant interface to interact with MemOS API via CLI tools and memory handling endpoints.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can connect to the MemOS API MCP server via a command-line MCP client. This MCP server provides a typed, CLI-based interface to interact with MemOS API using MCP standards, enabling you to send messages, search memories, and retrieve conversation history in a structured way.

How to use

You will run the MCP client that points to the MemOS API MCP server. Use the same environment variables across all commands to authenticate and identify the user. Start by setting your API key, a stable user identifier, and the site context where you are using this service. Then you can add messages to conversations, search conversation memories, or fetch messages, all through the MCP client.

How to install

Prerequisites: Node.js version 18 or newer. You also need either npm or pnpm installed.

Install the MCP package globally with npm or pnpm.

Then run the MCP CLI to start using the server.

Configuration and usage details

{
  "mcpServers": {
    "memos_api": {
      "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"
      }
    }
  }
}

Security and best practices

Keep your MEMOS_API_KEY secret. Do not hard-code credentials in code that could be committed to a repository. Use environment variables or a secure secrets manager in deployment environments.

Available tools

add_message

Adds a new message to a conversation by specifying the conversation_id and an array of messages with role and content.

search_memory

Searches for memories within a conversation using a query and memory_limit_number to limit results.

get_message

Retrieves messages from a specified conversation by providing the conversation_id.