
Openroad Mcp
io.github.The-OpenROAD-ProjectPublished by GitHub account The-OpenROAD-Projectv1.1.0Updated Oct 24, 2026
The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
Overview
Lets an AI assistant run and manage interactive OpenROAD physical-design sessions and inspect ORFS reports.
- What you can do
- The server exposes tools for interactive OpenROAD EDA sessions: it can create, list, inspect, and terminate sessions, run commands through a PTY, and query session state. It also returns command history and performance metrics, and can list and read report images produced by OpenROAD-flow-scripts runs. A query tool rejects state-modifying commands, which must go through the exec tool instead.
- When to use it
- Use it when an assistant needs to drive OpenROAD or ORFS digital-design flows, run RTL-to-GDSII steps, or review run reports and metrics without leaving the chat. It suits chip-design and EDA workflows rather than general software tasks.
- Requirements
- Runs locally over stdio, typically via npx with Node.js 22 or newer, or as a Docker image. OpenROAD must be installed and discoverable on PATH; ORFS is optional but recommended, with ORFS_FLOW_PATH defaulting to ~/OpenROAD-flow-scripts/flow. No accounts, API keys, or headers are declared.
Installation
In SourceWeft
- Open Openroad Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
OpenROAD MCP Server
A Model Context Protocol (MCP) server that provides tools for interacting with OpenROAD and ORFS.
About OpenROAD MCP
New here? Check out the Quick Start Guide to get your AI assistant analyzing designs in 5 minutes.
OpenROAD MCP eliminates the barrier between your AI assistant and physical design by connecting Claude, Cursor, and other MCP-compatible clients directly to the OpenROAD layout tools.
OpenROAD is the leading open-source, foundational application for semiconductor digital design, delivering an Autonomous, No-Human-In-Loop (NHIL) flow from RTL-GDSII. OpenROAD-flow-scripts (ORFS) is the fully autonomous flow built around it.
With this MCP server, your AI assistant can:
- Execute Commands - Run interactive OpenROAD sessions with full PTY support.
- Manage Sessions - Create, list, inspect, and terminate multiple physical design sessions.
- Track History & Metrics - Access full command history and performance metrics for analysis.
- Visualize Reports - List and read report images from ORFS runs directly in the chat.
Demo
Requirements & Installation
To use this MCP server, you need the server runtime, plus the underlying OpenROAD layout tools.
1. Server Runtime
- Node.js 22+ is required to run the
npxdistribution.
2. OpenROAD
OpenROAD must be installed and available in your PATH.
3. OpenROAD-flow-scripts (ORFS)
ORFS is optional but highly recommended for complete RTL-to-GDS flows and report visualization.
Configuration
For platform-specific Node.js and C++ toolchain setup instructions, see the Cross-Platform Build Guide.
You do not need to clone this repo or pass path environment variables in the common case. The published npx package does not read a .env file.
On startup the server inherits the MCP client's environment, then fills PATH the same way which openroad would: current PATH, then your login-shell PATH, then common install locations (/opt/homebrew/bin, conda, local OpenROAD builds). ORFS_FLOW_PATH defaults to ~/OpenROAD-flow-scripts/flow, and is also detected when ORFS sits next to the openroad binary.
Supported MCP Clients
Here is the standard base configuration used across most clients:
Find your specific client below for the exact configuration snippet and file location.
Claude Code
Or add the standard config to .mcp.json / .claude/settings.json.
If a GUI-launched client still cannot find openroad, pass an override. Use command -v so you do not hard-code paths:
Put --transport between --env and the server name so the CLI does not treat the name as another KEY=value pair.
Claude Desktop
Add the standard config to:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Cursor
Add the standard config to .cursor/mcp.json.
GitHub Copilot (VS Code)
Add to .vscode/mcp.json. Requires "type": "stdio":
Windsurf
Add the standard config to ~/.codeium/windsurf/mcp_config.json.
Cline / Roo Code
Add the standard config to cline_mcp_settings.json (Cline) or .roo/mcp.json (Roo Code).
Continue / PearAI
Add to your respective config.json under modelContextProtocolServers:
Zed
Add to ~/.config/zed/settings.json:
Docker / MCP Registry / Others
The server is available on the MCP Registry and via Docker:
Most other standard STDIO clients are fully supported. Refer to your tool's MCP setup guide.
Available Tools
Once configured, your AI assistant will have access to the following tools. For detailed parameters, schemas, and return formats, see the API Reference.
interactive_openroad_queryinteractive_openroad_execcreate_interactive_sessionlist_interactive_sessionsterminate_interactive_sessioninspect_interactive_sessionget_session_historyget_session_metricslist_report_imagesread_report_image
Troubleshooting
- The server fails to start: Ensure you have Node.js 22+. Older versions will fail.
- Session creation fails: Confirm
command -v openroadworks in a terminal. The server inherits PATH and searches common install locations; if your prefix is unusual, passPATHwith--envas shown in the Claude Code section. - Commands rejected with CommandBlocked: You sent a state-modifying command to
interactive_openroad_query. Useinteractive_openroad_execinstead. - Report images not found: The server defaults to
~/OpenROAD-flow-scripts/flow. If ORFS lives elsewhere, setORFS_FLOW_PATHin the MCP client'senvblock (not a.envfile).
To get more detail, set LOG_LEVEL=DEBUG in the server's environment.
Development
Clone the repository. .env.example is a local-dev reference only; copy it to .env if you use direnv or similar. The server still reads process.env (the MCP client's env block), not the file.
Then run:
Testing:
Linting & type checking:
Contributing
We welcome contributions! Please see CONTRIBUTING.md for detailed instructions on our development workflow and code standards.
License
BSD 3-Clause License. See LICENSE file.
Built with ❤️ by Precision Innovations
Source: README.md at commit c366bb5
Tools
0Version history
1- v1.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts