About Nourva Mind
Nourva Mind is a remote memory service for agents, letting users recall personal context and resume saved work across AI apps on request. It separates read access from reviewed memory proposals and saved work entries.
Key features
- 01Recall personal context on request
- 02List and check stored memory
- 03Resume saved work journal entries
- 04Propose facts for review
- 05Save or delete work entries
Use cases
- 01Recall project preferences in an AI app
- 02Continue work saved in another app
- 03Review stored memory before adding facts
MCP support
Connects agents to Nourva Mind through its remote MCP server. It exposes read and write tools for memory and work journal operations; OAuth 2.1 with PKCE handles authorization.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://nourva.ai/m/v1/mcpclaude mcp add --transport http ai-nourva-mind https://nourva.ai/m/v1/mcp{"mcpServers":{"ai-nourva-mind":{"type":"http","url":"https://nourva.ai/m/v1/mcp"}}}Open in Cursor{"servers":{"ai-nourva-mind":{"type":"http","url":"https://nourva.ai/m/v1/mcp"}}}Open in VS Code{"mcpServers":{"ai-nourva-mind":{"type":"http","url":"https://nourva.ai/m/v1/mcp"}}}{"mcpServers":{"ai-nourva-mind":{"serverUrl":"https://nourva.ai/m/v1/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMENourva Mind
Plugin that connects agents to Nourva Mind, your private memory across AI apps, through Nourva's official remote Model Context Protocol server.
Recall what matters about you, such as your work, projects, preferences and plans, and continue saved work from any app, only when you ask.
Install
- Open Settings → Plugins.
- Search for Nourva Mind.
- Click Install, then complete the Nourva sign-in prompt and press Allow.
MCP
{
"mcpServers": {
"nourva-mind": {
"type": "http",
"url": "https://nourva.ai/m/v1/mcp"
}
}
}
Auth is OAuth 2.1 with PKCE and dynamic client registration. No API key or client ID to configure.
What agents can do
| Tool | Kind | What it does |
|---|---|---|
nourva_memory_recall | read-only | Recall the user's own context when they ask about themselves |
nourva_memory_ledger | read-only | List what the memory holds |
nourva_memory_status | read-only | How much the memory holds and the plan's limits |
nourva_memory_resume | read-only | Continue saved work from the private work journal |
nourva_memory_propose | write | Propose a lasting fact the user stated; reviewed before it is kept |
nourva_memory_save | write | Save where the work stands to the work journal |
nourva_memory_forget_work | destructive | Delete one work journal entry |
The hosted server is the source of truth for tool names and schemas.
Privacy
- Tool calls run as the Nourva user who authorizes the connection, and see only that user's memory.
- Nothing is read from the host app's chats; only what the user asks to keep is saved.
- Keys, passwords and government ID numbers are removed before anything is saved.
- Policy: https://nourva.ai/policy#mind-apps · Terms: https://nourva.ai/terms
Support
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.