membase mcp server
About
A lightweight decentralized memory gateway that connects AI agents to Membase for persistent, verifiable multi-session memory.
Details
- Author
- unibaseio
- GitHub stars
- 24
- Downloads
- 162
- Categories
- Database, Other, File Management
Jump to
- 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.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
membase mcp serverCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"membase mcp server": {
"membase-mcp": {
"command": "uv",
"args": [
"run",
"src/membase_mcp/server.py"
]
}
}
}
}McpServers
{
"membase-mcp": {
"command": "uv",
"args": [
"run",
"src/membase_mcp/server.py"
]
}
}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.
Messages or memoiries can be visit at:https://testnet.hub.membase.io/
- get_conversation_id: 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.
git clone https://github.com/unibaseio/membase-mcp.git cd membase-mcp uv run src/membase_mcp/server.py
- MEMBASE_ACCOUNT: your account to upload
- MEMBASE_CONVERSATION_ID: 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" } } } }
- get conversation id and switch conversation
Immutable ledger database with live synchronization
Infino — keyword, vector, hybrid, and SQL retrieval over data on object storage, for AI agents.
Infino — keyword, vector, hybrid, and SQL retrieval over data on object storage, for AI agents.
Official MCP server for the Nhost backend platform — manage Postgres data, GraphQL, auth, storage, migrations and Hasura metadata via AI assistants.
Run SQL queries on data in Amazon S3 using AWS Athena.
An MCP server for interacting with Azure Table Storage, requiring an Azure Storage connection string.
Manage multiple Fireproof JSON document databases with cloud sync capabilities.
An MCP server for interacting with Apache Iceberg catalogs and data lakes.
MCP Memory Server - Python Implementation
A Python implementation of the MCP memory server for knowledge graph storage and retrieval, using JSONL files for persistence.
Allow your agent to connect to Pocketbase with ease.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
