Session Saver

Saves AI sessions as Markdown files organized by IDE, date, and description for easy access and management.

javascript

2

GitHub Stars

javascript

Language

5 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": {
    "oscar-wang-xin-mcp-session-saver": {
      "command": "mcp-session-saver",
      "args": [],
      "env": {
        "MCP_SESSION_BASE_DIR": "D:\\\\MyProjects\\\\sessions"
      }
    }
  }
}

You can use MCP Session Saver to persist your AI conversation sessions as Markdown files organized by IDE, date, and session description. It helps you save, locate, and manage conversations across multiple IDEs with a simple, repeatable workflow.

How to use

After you configure MCP Session Saver in your IDE, you can save your current session, list saved sessions, or search content within sessions. Start by saving the session you just had, then use the list and search commands to quickly locate past conversations. You can read or delete sessions as needed to keep your collection organized.

Typical workflows you can perform include saving a new session with a descriptive title, listing all saved sessions to review what you have stored, and searching session content to find a specific topic or answer. These operations are designed to work across multiple IDEs that support MCP, such as Qoder, Cursor, Claude Desktop, Windsurf, Trae, Codebuddy, Lingma, Continue, and Aider.

How to install

Prerequisites: Node.js is required. Ensure you have Node.js version 16 or newer and npm installed on your system.

Option A: Using npx (Recommended) Add to your IDE MCP configuration:

{
  "mcpServers": {
    "session_saver": {
      "command": "npx",
      "args": ["-y", "mcp-session-saver"]
    }
  }
}

Option B: Global installation Install globally and configure MCP to run the local binary:

npm install -g mcp-session-saver

MCP Configuration:

{
  "mcpServers": {
    "session_saver": {
      "command": "mcp-session-saver"
    }
  }
}

Option C: Local installation

Install the package locally in your project and reference it through MCP:

npm install mcp-session-saver

Available tools

save_session

Saves the current AI conversation as a Markdown file in the organized storage structure.

list_sessions

Lists all saved session records with metadata such as IDE, date, and description.

search_sessions

Searches saved sessions by content, date, IDE, or description to quickly locate relevant conversations.

delete_session

Deletes a specified saved session from storage to keep your library clean.

organize_sessions

Automatically categorizes and organizes sessions by IDE, date, and description for easy navigation.