Best for
- Developers who want to visualize complex codebases
- Teams using AI coding assistants and wanting to review generated code
- Developers needing quick architecture and process diagrams
- Users concerned about local data processing and privacy
M
Mindpilot MCP
Community
See through your agent's eyes. Visualize legacy code, architect new systems, understand everything.
GitHub source repository ↗
48FMRS · D
Mindpilot MCP provides useful visualization for AI coding assistants, enabling local Mermaid diagram generation. It works well with multi-client sharing and export features, but anonymous usage tracking and local server may require caution.
Mindpilot MCP is an MCP server for generating and rendering Mermaid diagrams. It enables your AI coding assistant to create on-demand architecture, code, and process diagrams displayed in a local web app, allowing you to visually explore and understand codebases. All diagrams are processed locally and never sent to the cloud. It supports multiple clients sharing the same diagram collection and exporting diagrams as vector images.
Tools
The tool list has not been reviewed yet.
Setup
### Claude Code
Run claude mcp add mindpilot -- npx @mindpilot/mcp@latest
### Cursor
Under Settings > Cursor Settings > MCP, add a global MCP server with the following configuration:
{
"mcpServers": {
"mindpilot": {
"command": "npx",
"args": ["@mindpilot/mcp@latest"]
}
}
}### VS Code
Follow the [VS Code MCP guide](https://code.visualstudio.com/docs/copilot/chat/mcp-servers) to enable MCP, then add to settings json:
{
"mcp": {
"servers": {
"mindpilot": {
"type": "stdio",
"command": "npx",
"args": ["@mindpilot/mcp@latest"]
}
}
}
}### Windsurf
Under Settings > Windsurf Settings > Manage Plugins, view raw config and configure in the mcpServers object.
### Zed
In the AI Thread panel, click the three dots ..., then select Add Custom Server..., enter npx @mindpilot/mcp@latest in the command field.
claude_desktop_config.json
{
"mcpServers": {
"mindpilot": {
"command": "npx",
"args": [
"@mindpilot/mcp@latest"
]
}
}
}
Fit and risk
Not for
- Users who don't need visual diagrams or charting capabilities
- Teams with strict budgets that want to completely disable anonymous usage tracking
- Users needing cloud-based diagram sharing or collaboration
- Users unfamiliar with Mermaid diagram syntax (requires LLM to generate it)
Required permissions
- Local file system access: saves diagrams in `~/.mindpilot/data/` or custom data path
- Network: starts a local web server (default port 4000) to display diagrams
- Anonymous usage data collection: enabled by default, can be disabled with `--disable-analytics` flag
Risks and side effects
- Anonymous usage data collection by default: may not meet strict privacy requirements, but can be disabled with flag
- Local server listening on port 4000: may conflict with existing services
- Relies on LLM to generate valid Mermaid syntax: incorrect generation may fail to render
- Multi-client support means multiple sessions share the same server; data might be unintentionally exposed to other local clients
Troubleshooting
- If port conflicts occur, use `--port 5555` to specify a different port.
- If using asdf and having MCP issues, set a global Node.js version from home directory (`asdf set nodejs x.x.x`).
- Ensure Node.js version is v20.0.0 or higher.
- If diagrams are not showing, check local web app at `http://localhost:4000` (or custom port).
- For development, run Claude with `--debug` flag to see MCP errors.
Use cases
Visualize the architecture of legacy codebases to quickly understand the system.
Generate a C4 context diagram of a project's architecture.
Show OAuth flow as a sequence diagram.
Inspect state machine for WebSocket connection logic.
Identify unused and redundant constructs in AI-generated code.
Supported clients
Claude DesktopFull support
VS CodeFull support
CursorFull support
WindsurfFull support
ZedFull support