membase mcp server
Description
Unibase membase is the first decentralized memory layer for AI agents. It stores historical information, interaction records, and persistent data of agents, ensuring their continuity and traceability.
The membase mcp server enables seamless integration with the membase protocol for decentralized storage. It provides functionality to upload and download memory to/from the Unibase DA network.
Functions
Messages or memoiries can be visit at: https://testnet.hub.membase.io/
- getconversationid: 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
- MEMBASECONVERSATIONID: 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

Membase Decentralized Memory Server
Project Details
Categories
Recomended MCP Servers
Linkup is a third-party extension that gives Claude access to real-time web search and premium content sources. It...
Un-official Serper Google search server for Cline and other MCP clients
An official Qdrant Model Context Protocol (MCP) server implementation
A MCP server for interacting with Bear note-taking software.
A Model Content Protocol server that provides tools to search and retrieve academic papers from PubMed database.
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
Ancestry MCP server made with Python that allows interactability with .ged (GEDCOM) files
MCP Server for interacting with LogSeq graph
🔍 Enable AI assistants to search and access bioRxiv papers through a simple MCP interface.





