Mode Manager

Provides persistent personal, workspace, and language-specific memories to keep Copilot aligned with your workflow.

other

10

GitHub Stars

other

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "niclasolofsson-mode-manager-mcp": {
      "command": "uvx",
      "args": [
        "mode-manager-mcp"
      ],
      "env": {
        "_RESTART": "1"
      }
    }
  }
}

Mode Manager MCP is an AI-powered memory and context system that helps you and your team remember important facts, preferences, and best practices so Copilot stays aligned with your workflow and your knowledge never gets lost.

How to use

Use Mode Manager MCP with your MCP client to persist personal, workspace, and language-specific memories. Speak naturally to save memories, and rely on the AI to load your memories automatically on each conversation.

How to install

Prerequisites: ensure you have Python installed on your system. If Python is not installed, download it from python.org and install Python 3.10 or higher.

If you do not have the runtime tool yet, install the MCP runner you prefer using one of the following approaches.

Option 1: One-Click Install (Easiest) – choose the appropriate MCP entry for your VS Code version and install. The server starts automatically when you open VS Code.

Configuration and runtime options

Multiple runtime configurations are shown for starting Mode Manager MCP. Each configuration uses a standard runtime command with arguments to run the MCP server. You can choose the one that matches your preferred toolchain.

{
  "servers": {
    "mode-manager": {
      "command": "uvx",
      "args": ["mode-manager-mcp"]
    }
  }
}

More advanced / development setups

If you want the bleeding-edge features directly from the Git repository, you can run the latest code from GitHub using uvx or pipx.

{
  "servers": {
    "mode-manager": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/NiclasOlofsson/mode-manager-mcp.git",
        "mode-manager-mcp"
      ]
    }
  }
}

For development and testing from GitHub

To run the latest code directly from GitHub using uvx, you can use the following configuration. You can also use pipx to run the same from the repository.

{
  "servers": {
    "mode-manager": {
      "command": "uvx",
      "args": [
        "run",
        "--with",
        "git+https://github.com/NiclasOlofsson/mode-manager-mcp.git",
        "mode-manager-mcp"
      ],
      "env": {
        "_RESTART": "1"
      }
    }
  }
}

Interactive onboarding

You can start onboarding from within your editor to set up persistent memory and preferences from the start.

Under the Hood: How memory works

Memory is organized into personal, workspace, and language-specific scopes. Each memory entry is stored as Markdown with a YAML frontmatter header and timestamped for easy auditing.

Contributing

Contributions are welcome. Your feedback and bug reports help drive improvements. You can contribute code or provide suggestions through the project’s contribution process.

License

MIT License - see the license file for details.