Packmind MCP server
{
"mcpServers": {
"packmind": {
"type": "http",
"url": "https://app.packmind.ai/mcp"
}
}
}{
"mcpServers": {
"packmind": {
"type": "http",
"url": "https://app.packmind.ai/mcp"
}
}
}{
"mcpServers": {
"packmind": {
"type": "http",
"url": "https://app.packmind.ai/mcp"
}
}
}{
"servers": {
"packmind": {
"type": "http",
"url": "https://app.packmind.ai/mcp"
}
}
}{
"mcpServers": {
"packmind": {
"type": "http",
"url": "https://app.packmind.ai/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
Packmind is a system for centralizing and distributing engineering standards, coding patterns, and AI agent instructions across your organization. It helps teams maintain a single source of truth for coding guidelines and automatically generates instruction files for different AI coding assistants (GitHub Copilot, Claude Code, Cursor, and others).
- Define your team's architecture rules, naming conventions, and best practices in one place, then automatically generate instruction files for each AI coding assistant your team uses.
- Sync engineering standards across multiple repositories without manually copying and maintaining separate instruction files in each project.
- Track which coding standards and commands are being used across your organization and monitor adoption across different repositories and AI tools.
Tools this server exposes
| Tool | Does |
|---|---|
| packmind-onboard | Command that helps create initial standards and commands by analyzing your codebase. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.