remember -vscode
Remember MCP, the VS Code extension that brings real, persistent memory to your AI assistant and your team. Instantly store preferences, facts, and best practices—so Copilot always knows your context, and your team’s knowledge is never lost.
claude mcp add --transport stdio niclasolofsson-remember-mcp-vscode pipx run --system-site-packages --spec git+https://github.com/NiclasOlofsson/mode-manager-mcp.git mode-manager-mcp
How to use
Remember MCP for VS Code integrates with the Mode Manager MCP server to enable persistent memory for Copilot and your team. The server, powered by the Mode Manager MCP project, stores personal, workspace, and language-specific memories that Copilot can consult on every turn. This extension registers the MCP server with VS Code so that the lifecycle is managed automatically by the editor, and you can control registration via the Remember MCP panel or commands. Once registered, memories you create or edit are saved as markdown with YAML frontmatter, and are loaded into Copilot context to improve suggestions and reduce repetitive questions.
To use the capabilities, first ensure the MCP server is registered through VS Code (Remember MCP panel or the relevant Command Palette actions). You can monitor Copilot usage, manage personal and team memories, and organize language-specific tips directly in your workspace. The extension supports creating and editing .chatmode.md and .instructions.md files to tailor prompts and chat modes for different scenarios. The server is designed to be transparent: VS Code handles server lifecycle, and Copilot automatically discovers and utilizes your memory when performing code or documentation tasks.
How to install
Prerequisites:
- Visual Studio Code installed
- Internet access to fetch the MCP server from GitHub
- Python 3.10+ and pipx (the manual path uses pipx; the extension may install it automatically)
Manual installation steps:
- Ensure Python is installed
- Visit https://www.python.org/downloads/ and install Python 3.10+ if not already present.
- Install pipx
- Run: ```bash pip install pipx
3) Install and run the MCP server via pipx
- Run: ```bash
pipx run --system-site-packages --spec git+https://github.com/NiclasOlofsson/mode-manager-mcp.git mode-manager-mcp
- Install the Remember MCP VS Code extension from the marketplace and follow the prompts to register the MCP server.
- In VS Code, open Settings and verify the Remember MCP server command is configured (or use the Remember MCP commands to Register/Show the MCP panel).
Additional notes
Tips and notes:
- The server is registered using the pipx-based command specified in the configuration; if you customize installation paths, adjust the command accordingly.
- Memory files are stored as Markdown with YAML frontmatter; regular backups of your workspace memories are recommended.
- Ensure Python 3.10+ and pipx are available when troubleshooting registration issues. The Troubleshooting section in the extension provides common checks (Python version, pipx availability, and server help).
- If you update the mode-manager-mcp source, re-run the installation instruction to pick up changes.
- The environment block is currently empty; you can add variables if your deployment requires specific paths or tokens (e.g., for private repos).
- This MCP setup relies on VS Code to manage the server lifecycle; you typically do not need to start/stop the server manually.
Related MCP Servers
mcp-graphql
Model Context Protocol server for GraphQL
mcp -azure-devops
An MCP server for Azure DevOps
BifrostMCP
VSCode Extension with an MCP server that exposes semantic tools like Find Usages and Rename to LLMs
rohlik
MCP server that lets you shop groceries across the Rohlik Group platforms (Rohlik.cz, Knuspr.de, Gurkerl.at, Kifli.hu, Sezamo.ro)
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.
mcp-gemini
This project provides a dedicated MCP (Model Context Protocol) server that wraps the @google/genai SDK. It exposes Google's Gemini model capabilities as standard MCP tools, allowing other LLMs (like Cline) or MCP-compatible systems to leverage Gemini's features as a backend workhorse.