unibaseio/membase-mcp logo

unibaseio/membase-mcp

Free

通过 Membase 以分布式方式保存和查询你的 Agent 记忆。

FreeFree tier
Type
Open Source
Company
Unibase

About unibaseio/membase-mcp

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.

Key Features

Decentralized memory layer for AI agents
Secure, persistent storage for conversation history, interaction records, and knowledge
Multi-session memory support for agent continuity
Provides MCP server functions: get_conversation_id, switch_conversation, save_message, get_messages
Verifiable storage on the Unibase DA network
Open source, written in Python

Pros & Cons

Pros
  • Lightweight and easy to set up
  • Open source with no licensing restrictions
  • Decentralized and verifiable memory storage
  • Free to use
  • Integrates with AI tools via the standard MCP protocol
  • Supports multi-session conversations
Cons
  • Requires manual configuration of environment variables
  • Currently uses a testnet, may not be production-ready
  • No official releases or packages published yet
  • Limited to Python environment and uv dependency
  • Documentation is limited to the README

Best For

Providing persistent memory for AI agents across multiple sessionsDecentralized and verifiable storage of agent conversation historyEnabling agent personalization and continuityStoring interaction records for traceability

FAQ

What is Membase?
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.
What functions does the Membase-MCP server provide?
It provides get_conversation_id, switch_conversation, save_message, and get_messages functions for managing agent memory.