mcpField
M
mem0 MCP Server

mem0 MCP Server

Local
github.com/sadiuysalMemory & Knowledge1Updated 84w ago
Repository

About mem0 MCP Server

mem0 MCP Server is a TypeScript MCP server that connects Mem0 memory streams to compatible tools. It supports creating, updating, searching, reading, and deleting streams, with stream access through resources.

Key features

  1. 01Create and append to memory streams
  2. 02Search memories semantically
  3. 03Read and delete streams
  4. 04Access streams as resources

Use cases

  1. 01Store conversation content in memory streams
  2. 02Search Mem0 memories by query
  3. 03Read or remove a specific stream

MCP support

It exposes memory stream operations as MCP tools and provides stream content and listings as resources.

#mem0#mcp-server#typescript

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mem0 MCP Server

A TypeScript implementation of the Model Context Protocol (MCP) server for mem0, providing memory stream functionality with Mem0 integration.

Features

  • Create memory streams with Mem0 integration
  • Append content to memory streams
  • Search memories using Mem0's semantic search
  • Read from memory streams
  • Resource-based access to memory streams
  • Delete memory streams

Prerequisites

  1. Node.js and npm installed
  2. Mem0 API key (get one from mem0.ai)

Installation

npm install

Configuration

Set your Mem0 API key as an environment variable:

export MEM0_API_KEY=your-api-key-here

Building

npm run build

Running the Server

npm start

Testing

Run the test client to verify server functionality:

npm test

API

Tools

  1. create-memory-stream

    • Parameters:
      • name: string
      • initialContent: string (optional)
      • userId: string (optional) - Mem0 user ID
      • agentId: string (optional) - Mem0 agent ID
    • Returns: Stream ID and metadata

  2. append-to-stream

    • Parameters:
      • streamId: string
      • content: string
      • role: "user" | "assistant" (optional)
    • Returns: Success confirmation

  3. search-memories

    • Parameters:
      • query: string
      • userId: string
      • agentId: string (optional)
      • threshold: number (optional)
    • Returns: Search results from Mem0

  4. read-stream

    • Parameters:
      • streamId: string
      • startIndex: number (optional)
      • endIndex: number (optional)
    • Returns: Stream content

  5. delete-stream

    • Parameters:
      • streamId: string
    • Returns: Deletion confirmation
Resources
  • memory://{streamId} - Access memory stream content directly
  • memory:// - List all memory streams

Development

The server is implemented using the MCP TypeScript SDK and provides integration with Mem0 for persistent memory storage and semantic search. To extend the implementation:

  1. Add more Mem0 features (e.g., memory tagging, metadata)
  2. Implement proper error handling
  3. Add authentication and authorization
  4. Add additional memory operations

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.