来当MCP模式

Requirements

• OpenROAD installed and available in your PATH
• Installation guide
• OpenROAD-flow-scripts (ORFS) for complete RTL-to-GDS flows (optional but recommended)
• ORFS installation guide
• Python 3.13+ or higher
• uv package manager
• Install: curl -LsSf https://astral.sh/uv/install.sh | sh

Getting Started

New to OpenROAD MCP? Check out our Quick Start guide.

For platform-specific setup instructions, see the Cross-Platform Guide.

Installation

<details> <summary><b>Claude Code</b></summary>

claude mcp add --transport stdio openroad-mcp -- uvx --from git+https://github.com/luarss/openroad-mcp openroad-mcp

Or add the standard configuration to .claude/settings.json.

</details>

<details> <summary><b>Claude Desktop</b></summary>

Add the standard configuration to: - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json - Windows: %APPDATA%\Claude\claude_desktop_config.json

</details>

<details> <summary><b>Cursor</b></summary>

Add the standard configuration to .cursor/mcp.json.

</details>

<details> <summary><b>GitHub Copilot (VS Code)</b></summary>

Add to .vscode/mcp.json (VS Code 1.99+). Note the different schema — servers key and "type": "stdio" required:

{
  "servers": {
    "openroad-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/luarss/openroad-mcp",
        "openroad-mcp"
      ]
    }
  }
}

</details>

<details> <summary><b>Gemini CLI</b></summary>

Follow the Gemini MCP install guide, using the standard configuration above.

</details>

<details> <summary><b>Windsurf</b></summary>

Add the standard configuration to ~/.codeium/windsurf/mcp_config.json.

</details>

<details> <summary><b>Cline</b></summary>

Add to the Cline MCP settings file: - macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json - Windows: %APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json - Linux: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

{
  "mcpServers": {
    "openroad-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/luarss/openroad-mcp",
        "openroad-mcp"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

</details>

<details> <summary><b>Roo Code</b></summary>

Add to .roo/mcp.json in your project root (or the equivalent user-level settings file via the Roo Code UI):

{
  "mcpServers": {
    "openroad-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/luarss/openroad-mcp",
        "openroad-mcp"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

</details>

<details> <summary><b>Continue</b></summary>

Add to ~/.continue/config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "uvx",
          "args": [
            "--from",
            "git+https://github.com/luarss/openroad-mcp",
            "openroad-mcp"
          ]
        }
      }
    ]
  }
}

</details>

<details> <summary><b>Zed</b></summary>

Add to ~/.config/zed/settings.json:

{
  "context_servers": {
    "openroad-mcp": {
      "command": {
        "path": "uvx",
        "args": [
          "--from",
          "git+https://github.com/luarss/openroad-mcp",
          "openroad-mcp"
        ]
      },
      "settings": {}
    }
  }
}

</details>

<details> <summary><b>JetBrains AI Assistant</b></summary>

Open Settings → Tools → AI Assistant → Model Context Protocol (MCP) and add a new server entry using the standard configuration.

</details>

<details> <summary><b>Amazon Q Developer CLI</b></summary>

Add the standard configuration to ~/.aws/amazonq/mcp.json.

</details>

<details> <summary><b>Augment Code</b></summary>

Add to your VS Code settings.json (User or Workspace scope):

{
  "augment.advanced": {
    "mcpServers": [
      {
        "name": "openroad-mcp",
        "command": "uvx",
        "args": [
          "--from",
          "git+https://github.com/luarss/openroad-mcp",
          "openroad-mcp"
        ]
      }
    ]
  }
}

</details>

<details> <summary><b>Warp</b></summary>

Open Settings → AI → MCP Servers → Add New MCP Server and enter: - Name: openroad-mcp - Command: uvx - Args: --from git+https://github.com/luarss/openroad-mcp openroad-mcp

</details>

<details> <summary><b>Amp</b></summary>

amp mcp add openroad-mcp uvx --from git+https://github.com/luarss/openroad-mcp openroad-mcp

</details>

<details> <summary><b>Trae</b></summary>

Add the standard configuration to the MCP section of Trae's user settings (accessible via Settings → MCP).

</details>

<details> <summary><b>Opencode</b></summary>

Add to opencode.json in your project root:

{
  "mcp": {
    "openroad-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "--from",
        "git+https://github.com/luarss/openroad-mcp",
        "openroad-mcp"
      ],
      "enabled": true
    }
  }
}

</details>

<details> <summary><b>Kiro</b></summary>

Open the MCP configuration panel in Kiro and add a new server entry using the standard configuration.

</details>

<details> <summary><b>Kilo Code</b></summary>

Add to .kilocode/mcp.json in your project root:

{
  "mcpServers": {
    "openroad-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/luarss/openroad-mcp",
        "openroad-mcp"
      ],
      "alwaysAllow": [],
      "disabled": false
    }
  }
}

</details>

<details> <summary><b>Docker</b></summary>

🚧 Work in Progress: Docker deployment via GitHub Container Registry (GHCR) is coming soon.

</details>

<details> <summary><b>MCP Registry</b></summary>

Once published to the MCP Registry, clients can discover and install directly:

uvx openroad-mcp

</details>

Setup

```bash

Install environment

uv venv make sync ```

Demo

Watch full demo video

Standard Configuration

The basic configuration for all MCP clients:

{
  "mcpServers": {
    "openroad-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/luarss/openroad-mcp",
        "openroad-mcp"
      ]
    }
  }
}

For local development, use:

{
  "mcpServers": {
    "openroad-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/openroad-mcp",
        "run",
        "openroad-mcp"
      ]
    }
  }
}

Run core tests (recommended - excludes PTY tests that may fail in some environments)

make test

Troubleshooting

If the MCP server fails to start:

1. Ensure uv is installed and available in your PATH
2. Verify the path to openroad-mcp is correct
3. Check that all dependencies are installed: make sync
4. Review your MCP client logs for specific error messages