MCP.so
ログイン

membase mcp server

@unibaseio

membase mcp server について

A lightweight decentralized memory gateway that connects AI agents to Membase for persistent, verifiable multi-session memory.

基本情報

カテゴリ

その他

ランタイム

python

トランスポート

stdio

公開者

unibaseio

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "membase-mcp": {
      "command": "uv",
      "args": [
        "run",
        "src/membase_mcp/server.py"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is membase mcp server?

Membase is a decentralized memory layer for AI agents, powered by Unibase. The Membase-MCP Server integrates with the Membase protocol to let agents upload and retrieve memories from the Unibase DA network for persistent, verifiable storage.

How to use membase mcp server?

Clone the repository, set the required environment variables (MEMBASE_ACCOUNT, MEMBASE_CONVERSATION_ID, MEMBASE_ID), then run uv run src/membase_mcp/server.py. Configure the server in your MCP client (Claude, Windsurf, Cursor, Cline) using the provided JSON. In an LLM chat, call the exposed functions: get_conversation_id, switch_conversation, save_message, get_messages.

Key features of membase mcp server

  • Decentralized memory layer for AI agents.
  • Secure persistent storage for conversation history.
  • Upload and retrieve memories from Unibase DA network.
  • Manage conversations with switch and ID functions.
  • Save and retrieve messages per conversation.

Use cases of membase mcp server

  • Maintain agent continuity across sessions by storing conversation history.
  • Provide personalized interactions by recalling past memories.
  • Enable traceability of agent decisions through verifiable storage.
  • Switch between different conversations to handle multiple contexts.

FAQ from membase mcp server

How do I view stored messages or memories?

Messages or memories can be visited at https://testnet.hub.membase.io/.

What environment variables are required?

MEMBASE_ACCOUNT (your account), MEMBASE_CONVERSATION_ID (unique conversation ID), and MEMBASE_ID (your instance ID) must be set.

How do I install and run the server?

Clone the repository, then run uv run src/membase_mcp/server.py after setting the required environment variables.

What functions does the server expose?

It exposes get_conversation_id, switch_conversation, save_message, and get_messages for managing conversations and memories.

コメント

「その他」の他のコンテンツ