uml-memory 0.2.0

MCP server for Unified Memory Layer — persistent memory across AI coding tools

uml-memory

MCP server for Unified Memory Layer — persistent memory across AI coding tools.

Quick Start

pip install uml-memory

Add to your MCP config (~/.cursor/mcp.json for Cursor):

{
  "mcpServers": {
    "uml": {
      "command": "uvx",
      "args": ["uml-memory"],
      "env": {
        "UML_API_URL": "https://your-server.com",
        "UML_API_TOKEN": "your-token-here"
      }
    }
  }
}

Restart your IDE. The MCP tools will appear automatically.

What It Does

Once configured, your AI coding agent will automatically:

• Compose context at the start of every task (loads relevant decisions, constraints, and patterns)
• Save memories when important decisions or insights emerge during conversations
• Check lessons learned before risky operations like deployments or migrations

Available Tools

Tool	Description
uml_compose	Load relevant context at the start of a task
uml_save_memory	Save a decision, constraint, or insight
uml_search	Search memories by keyword or meaning
uml_list_projects	List all projects with saved memories
uml_save_conversation	Extract insights from a conversation
uml_detect_memories	Analyze text for high-value content
uml_check_lessons	Check lessons learned before risky operations
uml_generate_rules	Generate AGENTS.md or .cursor/rules from memories
uml_import_transcript	Import conversation transcripts

Getting Your Token

1. Log in to your UML instance
2. Go to Settings
3. Click Generate API Token
4. Copy the token into your mcp.json