# Contemplation

> Use this tool when you need to enable continuous cognitive processing and background analysis for AI assistants, solving problems such as context loss between conversations and incomplete insight generation. It takes in thoughts and ideas, processes them asynchronously using local Ollama models, and outputs high-significance insights saved to Obsidian and medium-significance thoughts stored temporarily. Ideal for use cases requiring persistent subprocesses that build context and surface relevant patterns across conversations and sessions.

Canonical page: https://skillsregistry.net/skills/contemplation  
JSON: https://api.skillsregistry.net/v1/skills/contemplation

## Description

This MCP server provides AI assistants with access to Claude's background contemplation loop - a persistent subprocess that processes thoughts asynchronously between conversations using local Ollama models for different thinking styles. The implementation manages four types of thoughts (patterns, connections, questions, general) with configurable significance thresholds, automatically aggregates similar insights to prevent repetition, and saves high-significance insights permanently to Obsidian while storing medium-significance thoughts in temporary scratch storage for 4 days. Built with intelligent memory management that prunes old insights and learns from usage patterns, it serves users wanting continuous cognitive processing that builds context across conversations, teams needing persistent insight generation that survives between sessions, and workflows requiring background analysis that surfaces relevant patterns and connections when needed.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/contemplation)
- **Repository:** <https://github.com/mikeybeez/mcp-contemplation>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "contemplation"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/contemplation` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/contemplation/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt