Vvkmnn/claude-praetorian-mcp
⚜️ An MCP server for context compaction and recycling in Claude Code
Implements MCP-based context compaction using the TOON (Token-Oriented Object Notation) format to shrink conversation histories and task outputs by 90%+ before context exhaustion. It persists structured snapshots to `.claude/praetorian/` as flat files, enabling selective restoration of research findings, architecture decisions, and subagent outputs into fresh context windows. Integrates with Claude Code through optional skills and hooks that automatically trigger compaction after expensive operations like web searches and subagent tasks.
Available on npm.
Stars
13
Forks
1
Language
TypeScript
License
MIT
Category
Last pushed
Feb 21, 2026
Commits (30d)
0
Dependencies
3
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/Vvkmnn/claude-praetorian-mcp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deus-h/claudeus-wp-mcp
Claudeus WordPress MCP Server
minipuft/claude-prompts
MCP prompt template server: hot-reload, thinking frameworks, quality gates
regen-network/regen-compute
An MCP agent that funds verified ecological regeneration from AI compute usage via Regen Network
regression-io/coder-config
Configuration manager for AI coding tools - Claude Code, Gemini CLI, Codex CLI, Antigravity....
Lykhoyda/ask-llm
MCP server for AI-to-AI collaboration — bridge Claude with Gemini, Codex, and other LLMs for...