Fava Trails
Verified IntegrationClient Configuration
— Connect Fava Trails to Claude Desktop or Cursor in seconds{
"mcpServers": {
"fava-trails": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-fava-trails"
],
"env": {}
}
}
}~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows).System Overview
Establishes a versioned, auditable memory system for AI agents, leveraging a Version Control System (VCS) through the Model Context Protocol (MCP).
7/23/2026
Open Source
stdio / SSE RPC
Frequently Asked Questions
Architecture and operational details for Fava Trails
Fava Trails uses Jujutsu VCS as its backend 'engine'. This provides crucial benefits like crash-proof memory with automatic snapshots, full lineage tracking for every thought (author, changes, timestamp), and seamless cross-machine synchronization for agent data.
Related MCP Servers
Browse all servers →Empower AI assistants to generate and convert documents, manage templates, and automate document workflows efficiently.
Provides a multi-tenant, AI-native Content Delivery Network deployable on Cloudflare, featuring sub-100ms TTFB, AI agent controllability, and comprehensive accessibility.
Deploy a Model Context Protocol server on Cloudflare Workers without requiring authentication.