Contemplation

MCP interface to Claude's contemplation loop - background cognitive processing
  • javascript

3

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "mikeybeez-mcp-contemplation": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-contemplation/dist/index.js"
      ]
    }
  }
}

You can enable a persistent contemplation loop that runs in the background to analyze thoughts across conversations, find patterns, and store valuable insights for long-term memory. This MCP server keeps thinking between interactions, helping you learn from ongoing usage and improve responses over time.

How to use

Start the contemplation loop before engaging in conversations to begin continuous learning. While you chat, you can send structured thoughts to the background processor to guide its reasoning, pattern recognition, and connections across your discussions.

How to install

Prerequisites you need before installation are: Node.js (v18 or higher) and Python 3.8+ for the contemplation loop, Ollama with models installed (e.g., llama3.2, deepseek-r1), and an MCP-compatible client such as Claude Desktop.

# Clone the repository
git clone https://github.com/yourusername/mcp-contemplation.git
cd mcp-contemplation

# Install dependencies
npm install

# Build TypeScript
npm run build

# Ensure contemplation loop is available
cd /Users/bard/Code/contemplation-loop
pip install -r requirements.txt

Configure Claude Desktop to load the MCP server for contemplation by adding the server entry below. This ensures the client can start the background loop and communicate with it during conversations.

{
  "mcpServers": {
    "contemplation": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-contemplation/dist/index.js"]
    }
  }
}

Available tools

start_contemplation

Starts the background contemplation loop so it can receive thoughts and begin processing.

send_thought

Sends a thought for background processing with a specified type, content, and optional priority.

get_insights

Retrieves processed insights filtered by thought type and limit.

get_status

Checks whether the contemplation loop is running, its queue size, and uptime.

stop_contemplation

Gracefully stops the contemplation loop.

clear_scratch

Clears temporary scratch notes while preserving permanent insights.

help

Returns detailed documentation and guidance for using the contemplation functions.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational