An MCP server that provides shared persistent AI memory across clients like Claude, Cursor, VS Code, and ChatGPT. It lets agents write, read, rate, inspect, and delete memories through MCP tools backed by a Mnemoverse API key.
From the registry: Persistent memory across Claude, Cursor, ChatGPT, VS Code. Importance scoring, linked recall.
Please install the `mcp-memory-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Get a Mnemoverse API key** — Sign up at the Mnemoverse console and create an API key for the server. (https://console.mnemoverse.com/)
- **Install Node.js and npm** — Required to run the server via npx. (https://nodejs.org/)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@mnemoverse/mcp-memory-server@latest"]
- required environment variables:
- `MNEMOVERSE_API_KEY`: Mnemoverse API key used to authenticate the MCP server. (example: `<your-mnemoverse-api-key>`)
- optional environment variables:
- `MNEMOVERSE_API_URL`: Override the Mnemoverse API base URL. (example: `<your-mnemoverse-api-url>`)
Note: Use the stdio server via npx with the @latest suffix so npm checks for new releases on each client startup. Restart the MCP client after updating configuration.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MNEMOVERSE_API_KEYrequiredAPI key required to authenticate with the Mnemoverse memory serviceAI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.