广告合作
MCP.so
登录

membase MCP server

@unibaseio

代码仓库主页文档

基本信息

分类

记忆与知识

传输方式

stdio

作者

unibaseio

提交者

parasyte-x

关于 membase MCP server

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

membase MCP server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

membase MCP server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

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.

常见问题

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.

评论

记忆与知识 分类下的更多 MCP 服务器

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.

1

Memlord

MyrikLD

Memlord is a remote MCP server available at https://app.memlord.com.

AOCI-CODE

aoci-spec

Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

1.7K

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

广告合作