Openroad MCP server
io.github.The-OpenROAD-Project/openroad-mcp·v1.1.0·31 starsThe OpenROAD MCP server - interactive EDA sessions via Model Context Protocol
31 stars75 downloads/wk
Reviews
Write oneNobody has reviewed Openroad yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Openroad tools (15, 5 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
cancel_orfs_jobwrite actionTerminate a running flow job and every process it spawned, so no orphaned openroad
create_interactive_sessionwrite actionCreate a new interactive OpenROAD session.
get_orfs_jobPoll a flow run started by run_orfs_stage: status, elapsed time, the ORFS stage currently
get_session_historyGet command history for an interactive OpenROAD session.
get_session_metricsGet comprehensive metrics for all interactive OpenROAD sessions.
grep_session_outputSearch the output of commands already run in a session, without re-running them or
inspect_interactive_sessionGet detailed inspection data for an interactive OpenROAD session.
interactive_openroad_execwrite actionExecute a state-modifying OpenROAD command (set_*, create_*, read_*, write_*, flow commands).
interactive_openroad_querywrite actionExecute a read-only OpenROAD command (report_*, get_*, check_*, sta, help, etc.).
list_interactive_sessionsList all active interactive OpenROAD sessions.
list_report_imagesList available report images from ORFS runs organized by stage.
read_orfs_metricsRead an ORFS design's per-stage metrics, its rules-base.json gate thresholds evaluated
read_report_imageRead a report image (congestion, IR-drop, placement, clock tree) and return it as a
run_orfs_stagewrite actionRun an ORFS flow stage (synth, floorplan, place, cts, grt, route, finish, or a clean_*
terminate_interactive_sessionTerminate an interactive OpenROAD session.
Public scan report
scanner v0.1.10 · 2026-10-31 · same rubric, same numbers if you re-run it
- Code scan53 source files scanned15/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Findings (2)
- mediumnpm install lifecycle script present
install.script - mediumnpm install lifecycle script present
install.scriptpackage.json: …x-node-pty.cjs" ], "scripts": { "postinstall": "node scripts/fix-node-pty.cjs", "b…
How Openroad compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 4,461 AI and agents servers
- Tools
- 15
- the typical AI and agents server has 6
- Tools that change things
- 33%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 31
- more than 90% of 2,713 AI and agents servers
- Downloads a week
- 75
- more than 55% of 1,554 AI and agents servers with a package
What its tools let an agent do: 10 read · 1 create · 2 change · 1 delete · 1 run or deploy
Install Openroad in Claude Code, Cursor or VS Code
Runs npx -y openroad-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add openroad-mcp -- npx -y openroad-mcp
What the publisher says
From the Openroad repository's README, as published. We do not edit it. Read it on GitHub
OpenROAD MCP Server
<!-- mcp-name: io.github.The-OpenROAD-Project/openroad-mcp -->
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
Watch full demo video
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 npx distribution.
2. OpenROAD
OpenROAD must be installed and available in your PATH.
- Official OpenROAD Installation Guide
3. OpenROAD-flow-scripts (ORFS)
ORFS is optional but highly recommended for complete RTL-to-GDS flows and report visualization.
- Official ORFS Local Build Guide
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). ORFSFLOWPATH 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:
{
"command": "npx",
"args": ["-y", "openroad-mcp"]
}Find your specific client below for the exact configuration snippet and file location.
Claude Code
claude mcp add --transport stdio openroad-mcp -- npx -y openroad-mcpOr 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:
claude mcp add \
--env PATH="$(dirname "$(command -v openroad)"):${PATH}" \
--env ORFS_FLOW_PATH="${HOME}/OpenROAD-flow-scripts/flow" \
--transport stdio openroad-mcp \
-- npx -y openroad-mcpPut --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/claudedesktopconfig.json
- Windows: %APPDATA%\Claude\claudedesktopconfig.json
Cursor
Add the standard config to .cursor/mcp.json.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Openroad: common questions
- Is Openroad MCP server safe?
- Mostly: it is graded B (78/100). Read the Openroad safety report
- How do I install Openroad?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Openroad need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Openroad maintained?
- The last commit was 6 days ago (2026-10-31). The latest release is v1.1.0.
- What can I use instead of Openroad?
- Servers from other publishers that do the same job: Watch Skill MCP server, three.ws Avatars MCP server and Emulo MCP server.
- How does Openroad compare with other AI and agents MCP servers?
- safety score 78/100 (higher than 57% of 4,461 AI and agents servers); tools 15 (the typical AI and agents server has 6); tools that change things 33% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Openroad
Same job from other publishers: the closest match first, then the best rated.
- Watch SkillWatch video and live sessions, keep timestamped evidence, and verify an agent's own work.not reviewedEstablishedB
- three.ws Avatarsthree.ws 3D avatars in your agent: render a live, interactive 3D avatar inline, or get an embed.not reviewedEstablishedA
- EmuloMine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.not reviewedEstablishedA