Memos Api MCP Server

A Model Context Protocol (MCP) implementation for the [MemOS](https://github.com/MemTensor/MemOS) API service. This package provides a command-line

Local serverstdioTypeScript

What is the Memos Api MCP Server?

A Model Context Protocol (MCP) implementation for the MemOS API service. This package provides a command-line interface to

The short version

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

What it needs from you

  • Node.js >= 18 - npm or pnpm (recommended)

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
messagesArray of messages containing role and content information.
roleRole of the message sender (user or assistant).
contentMessage content.
chat_time(Optional) Message timestamp.
filter(Optional) Filter conditions, used to precisely limit the memory scope before retrieval.
knowledgebase_ids(Optional) Array specifying the knowledge bases to search.
include_preference(Optional) Enable preference memory recall. Default: true.
preference_limit_number(Optional) Max preference memories to return. Default: 9, max 25.
include_tool_memory(Optional) Enable tool memory recall. Default: false.
tool_memory_limit_number(Optional) Max tool memories to return. Default: 6, max 25.
include_skill(Optional) Enable Skill recall. Default: false.
skill_limit_number(Optional) Max Skills to return. Default: 6, max 25.
relativity(Optional) Relevance threshold (0-1) for recalled memories. A value of 0 disables relevance filtering.

How to install the Memos Api MCP Server

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

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

  • Node.js >= 18 - npm or pnpm (recommended)
VariableDescriptionRequired
MEMOS_API_KEYDeclared in the maintainer’s client configuration.Check documentation
MEMOS_USER_IDDeclared in the maintainer’s client configuration.Check documentation
MEMOS_CHANNELDeclared in the maintainer’s client configuration.Check documentation

Example prompts to try

  • “Use Memos Api MCP to Parameters.”
  • “Use Memos Api MCP to messages.”
  • “Use Memos Api MCP to role.”

Frequently asked questions

A Model Context Protocol (MCP) implementation for the [MemOS](https://github.com/MemTensor/MemOS) API service. This package provides a command-line interface to Confirm the tools offered by your installed version in the connected client. Tool availability and permissions depend on the server and account configuration.