io.github.onetrueclaude-creator/mcp-curiosity-engine
Surface the notes you forgot you wrote — DMN replay for markdown vaults.
Install
Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).
mcp-curiosity-engineclaude mcp add mcp-curiosity-engine -e 'CURIOSITY_ENGINE_LICENSE=<your curiosity_engine_license>' -- uvx mcp-curiosity-engine==0.1.0
{
"mcpServers": {
"mcp-curiosity-engine": {
"command": "uvx",
"args": [
"mcp-curiosity-engine==0.1.0"
],
"env": {
"CURIOSITY_ENGINE_LICENSE": "<your curiosity_engine_license>"
}
}
}
}
Environment variables
CURIOSITY_ENGINE_LICENSEsecret Pro license JWT (optional). Unlocks premium features. See README.
Documentation
From the project's README on GitHub, refreshed weekly. Links open on GitHub.
mcp-curiosity-engine
Surface the notes you forgot you wrote — DMN replay for markdown vaults.
Surface the notes you've forgotten you wrote. Uses wikilink graph structure + file mtime to identify dormant notes (low link-in count, old, isolated) and the DMN-inspired replay cycle pattern from cognitive neuroscience: sample dormant notes with bias (40% random / 30% least-linked / 30% orphaned), generate cross-domain bridge queries between them, and surface the unexpected connections. Breaks the confirmation-bias loop where you only revisit the notes you already remember.
Install
pip install mcp-curiosity-engine
# or
uvx mcp-curiosity-engine
Usage
Claude Code
claude mcp add mcp-curiosity-engine -- mcp-curiosity-engine
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"curiosity_engine": {
"command": "uvx",
"args": ["mcp-curiosity-engine"]
}
}
}
MCP Tools
| Tool | Tier | Description |
|---|---|---|
find_dormant_notes | Free | List notes that are structurally dormant — low incoming wikilink count AND old mtime. These are the notes most at risk of being forgotten. |
find_orphan_notes | Free | List notes with zero incoming wikilinks — structurally isolated, the extreme case of dormancy. |
suggest_replay_cycle | Pro | Run the full DMN-inspired replay cycle: sample dormant notes with bias (40% random / 30% least-linked / 30% orphans), extract their concepts, generate cross-domain bridge queries between them, return notes to revisit. The core moat. |
find_cross_domain_bridges | Pro | Surface pairs of notes from DIFFERENT top-level directories that share concepts. These are the surprise connections — ideas that span your vault's silos. |
random_deep_cut | Pro | Pull a single random dormant note for serendipitous rediscovery. Think of it as your vault's shuffle-play button. |
Pro tier
Unlocks the full DMN replay cycle, cross-domain bridge discovery, and random deep-cut sampling.
License activation — any one of these works:
# 1. Environment variable
export CURIOSITY_ENGINE_LICENSE="eyJhbGc..."
# 2. CLI flag
mcp-curiosity-engine --license-key "eyJhbGc..."
# 3. Config file
echo "eyJhbGc..." > ~/.mcp-curiosity-engine/license.jwt
Licenses are verified fully offline — no phone-home, no activation server. Get a license at **https://github.com/onetrueclaude-creator/mcp-curiosity-engine#pro-tier**.
Requirements
- Python 3.10+
License
MIT
Frequently asked questions
What is io.github.onetrueclaude-creator/mcp-curiosity-engine?
Surface the notes you forgot you wrote — DMN replay for markdown vaults.
How do I install io.github.onetrueclaude-creator/mcp-curiosity-engine?
It runs on your machine. In Claude Code: claude mcp add mcp-curiosity-engine -e 'CURIOSITY_ENGINE_LICENSE=<your curiosity_engine_license>' -- uvx mcp-curiosity-engine==0.1.0. For other clients, paste the JSON configuration from this page into their MCP settings.
Does io.github.onetrueclaude-creator/mcp-curiosity-engine need an API key?
Yes. It expects CURIOSITY_ENGINE_LICENSE, which you set in its configuration.
Is io.github.onetrueclaude-creator/mcp-curiosity-engine open source?
Yes. Its code is on GitHub under the MIT license.
Who maintains io.github.onetrueclaude-creator/mcp-curiosity-engine?
It is published by onetrueclaude-creator. AI.tn lists it but does not maintain or endorse it.
From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.