広告掲載
MCP.so
ログイン

membase MCP server

@unibaseio

リポジトリホームページドキュメント

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

unibaseio

投稿者

parasyte-x

membase MCP server について

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

membase MCP server の設定

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"
      ]
    }
  }
}

membase MCP server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

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.

よくある質問

1

How do I view stored messages or memories?

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

2

What environment variables are required?

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

3

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.

4

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

「メモリとナレッジ」の他のコンテンツ

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

M1K3

Round-Tower

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

7

Code Graph Rag

vitali87

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

5.3K

agentleFS

agentleFS

One permissioned folder your team and your AI agents both log into.

広告掲載