Nourva Mind

ai.nourvaPublished by nourva.aiOfficial publisherv1.0.0Updated Oct 30, 2026

Your private memory across AI apps: recall your context and continue saved work, only when you ask.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowKnowledge & Memory

Overview

AI-generated overview

Nourva Mind is a hosted memory service that lets an assistant recall your personal context and resume saved work across AI apps, only when you ask.

What you can do
  • Recall your own context about work, projects, preferences and plans when you ask about yourself
  • List what the memory holds and check how much it holds against the plan's limits
  • Continue saved work from a private work journal
  • Propose a lasting fact you stated, for review before it is kept
  • Save where the work stands to the work journal
  • Delete a single work journal entry
When to use it
Useful if you want continuity between different AI apps: an assistant can pick up your saved work and remember stated preferences without you repeating them. It is aimed at people who want memory that is only read when they explicitly ask for it.
Requirements
A remote MCP endpoint at nourva.ai, added as an HTTP server. Authentication is OAuth 2.1 with PKCE and dynamic client registration, so you sign in to a Nourva account and approve access; no API key or client ID is configured. Network access is required.
Before you install
The server stores personal context and a work journal tied to your Nourva account, and the write tools can add facts and journal entries while the forget tool deletes a journal entry. Proposals are reviewed before being kept, and keys, passwords and government ID numbers are said to be stripped before saving, but you should still avoid pasting secrets. Data is held by Nourva under its own policy and terms.

Installation

In SourceWeft

  1. Open Nourva Mind in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/ai.nourva%2Fmind/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "nourva-mind": {
      "type": "http",
      "url": "https://nourva.ai/m/v1/mcp"
    }
  }
}

README

Nourva 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

  1. Open Settings → Plugins.
  2. Search for Nourva Mind.
  3. Click Install, then complete the Nourva sign-in prompt and press Allow.

MCP

json
{  "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

ToolKindWhat it does
nourva_memory_recallread-onlyRecall the user's own context when they ask about themselves
nourva_memory_ledgerread-onlyList what the memory holds
nourva_memory_statusread-onlyHow much the memory holds and the plan's limits
nourva_memory_resumeread-onlyContinue saved work from the private work journal
nourva_memory_proposewritePropose a lasting fact the user stated; reviewed before it is kept
nourva_memory_savewriteSave where the work stands to the work journal
nourva_memory_forget_workdestructiveDelete 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

[email protected]

License

MIT

Source: README.md at commit aa5dba0

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestOct 30, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts