Contemplation
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- other
- Source
- PulseMCP
- Repository
- github.com/mikeybeez/mcp-contemplation
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Contemplation from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.