Membase

What is Membase-MCP?

Membase-MCP is a server that enables AI agents to seamlessly integrate with the Membase protocol. Membase itself is a decentralized memory layer for AI agents, powered by Unibase, providing secure, persistent storage for conversation history, interaction records, and knowledge. This ensures agent continuity, personalization, and traceability.

How to use Membase-MCP?

To use Membase-MCP, you first need to clone the repository and run the server:

git clone https://github.com/unibaseio/membase-mcp.git
cd membase-mcp
uv run src/membase_mcp/server.py

You will also need to configure environment variables such as MEMBASE_ACCOUNT, MEMBASE_CONVERSATION_ID, and MEMBASE_ID. The project provides configuration examples for platforms like Claude, Windsurf, Cursor, and Cline, showing how to set up the mcpServers.

Once set up, you can call functions within your LLM chat to interact with Membase. Examples include getting and switching conversation IDs, and saving/getting messages.

Key Features of Membase-MCP

• Decentralized Memory: Leverages Membase for decentralized, verifiable storage of AI agent memories.
• Persistent Storage: Provides secure and persistent storage for conversation history, interaction records, and knowledge.
• Agent Continuity: Ensures AI agent continuity through stored memory.
• Personalization: Enables personalized AI agent interactions.
• Traceability: Offers traceability of AI agent activities.
• Key Functions: Includes functions like get_conversation_id, switch_conversation, save_message, and get_messages.

Use Cases of Membase-MCP

Membase-MCP is ideal for scenarios where AI agents require:

• Long-term Memory: Storing and retrieving past conversations and interactions.
• Contextual Understanding: Maintaining context across multiple sessions.
• Personalized Experiences: Delivering tailored responses based on historical data.
• Auditable Interactions: Ensuring verifiable records of agent activities.
• Building Advanced AI Applications: Providing a foundational memory layer for complex AI systems.

FAQ from Membase-MCP

Q: Where can messages or memories be visited? A: Messages or memories can be visited at: https://testnet.hub.membase.io/

Q: What environment variables are required? A: MEMBASE_ACCOUNT, MEMBASE_CONVERSATION_ID, and MEMBASE_ID are required environment variables.

membase mcp server

Description

Membase is the first decentralized memory layer for AI agents, powered by Unibase. It provides secure, persistent storage for conversation history, interaction records, and knowledge — ensuring agent continuity, personalization, and traceability.

The Membase-MCP Server enables seamless integration with the Membase protocol, allowing agents to upload and retrieve memory from the Unibase DA network for decentralized, verifiable storage.

Functions

Messages or memoiries can be visit at: https://testnet.hub.membase.io/

• get_conversation_id: Get the current conversation id.
• switch_conversation: Switch to a different conversation.
• save_message: Save a message/memory into the current conversation.
• get_messages: Get the last n messages from the current conversation.

Installation

git clone https://github.com/unibaseio/membase-mcp.git
cd membase-mcp
uv run src/membase_mcp/server.py

Environment variables

• MEMBASE_ACCOUNT: your account to upload
• MEMBASE_CONVERSATION_ID: your conversation id, should be unique, will preload its history
• MEMBASE_ID: your instance id

Configuration on Claude/Windsurf/Cursor/Cline

{
  "mcpServers": {
    "membase": {
      "command": "uv",
      "args": [
        "--directory",
        "path/to/membase-mcp",
        "run", 
        "src/membase_mcp/server.py"
      ],
      "env": {
        "MEMBASE_ACCOUNT": "your account, 0x...",
        "MEMBASE_CONVERSATION_ID": "your conversation id, should be unique",
        "MEMBASE_ID": "your sub account, any string"
      }
    }
  }
}

Usage

call functions in llm chat

• get conversation id and switch conversation

• save message and get messages