Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.luarss/openroad-mcp

PYPI · OPENROAD-MCP · 2 COMPONENTS · SCANNED SEP 20

The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol

−15 this week 52 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security32
  • Malware scan not yet available for this package.Unverified
  • CVE check failed: a known high-severity CVE affects mcp 1.26.0, a direct dependency. A fixed version is available. View diagnostics → Fail
  • Runs hatchling.build at install time, a recognised native-build step with no shell scripting around it. View diagnostics → Pass
  • 3 of 63 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency10
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 444 tokens (~44/item across 10 items; 10 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
  • Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety92
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 2 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "interactive_openroad_query" implies "execute" and declares readOnlyHint instead, contradicting what its own name says it does. See how to fix → Partial
  • An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the io.github.luarss/openroad-mcp server?

io.github.luarss/openroad-mcp runs locally as a PyPI package, launched with uvx openroad-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · openroad-mcp

# add to Claude Code
claude mcp add luarss-openroad-mcp -- uvx openroad-mcp
// .cursor/mcp.json
{
  "mcpServers": {
    "luarss-openroad-mcp": {
      "command": "uvx",
      "args": [
        "openroad-mcp"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "luarss-openroad-mcp": {
      "command": "uvx",
      "args": [
        "openroad-mcp"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add luarss-openroad-mcp -- uvx openroad-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "luarss-openroad-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "openroad-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add luarss-openroad-mcp --command uvx --arg openroad-mcp
# ~/.hermes/config.yaml
mcp_servers:
  luarss-openroad-mcp:
    command: "uvx"
    args: ["openroad-mcp"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "luarss-openroad-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "openroad-mcp"
      ]
    }
  }
}
# add to Vellum
assistant mcp add luarss-openroad-mcp -t stdio -c uvx -a openroad-mcp
// mcp.json
{
  "mcpServers": {
    "luarss-openroad-mcp": {
      "command": "uvx",
      "args": [
        "openroad-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 −14
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • Malware scan: pass → unverified security
  • 19 Sept 26 +15
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • Malware scan: unverified → pass security
  • 18 Sept 26 +1
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55380 affects this package: high security
  • 17 Sept 26 −18
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • Malware scan: pass → unverified security
    • Stability: pass → 0.80 functional
  • 16 Sept 26 +15
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • Malware scan: unverified → pass security
    • Stability: 0.97 → pass security
  • 15 Sept 26 +1
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • CVE-2026-54059 affects this package: high security
  • 14 Sept 26 −15
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-54060 affects this package: high security
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • Malware scan: pass → unverified security
  • 13 Sept 26 +1
    • CVE-2026-59204 affects this package: high security
    • CVE-2026-52869 affects this package: high security
    • CVE-2026-52870 affects this package: high security
    • CVE-2026-59197 affects this package: high security
    • CVE-2026-55380 affects this package: high security
    • CVE-2026-59200 affects this package: high security
    • CVE-2026-55798 affects this package: high security
    • CVE-2026-55379 affects this package: high security
    • CVE-2026-59199 affects this package: high security
    • CVE-2026-54059 affects this package: high security
    • CVE-2026-59950 affects this package: high security
    • CVE-2026-59203 affects this package: high security
    • CVE-2026-54058 affects this package: high security
    • CVE-2026-59205 affects this package: high security
    • CVE-2026-59198 affects this package: high security
    • CVE-2026-54060 affects this package: high security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Analysed pypi/openroad-mcp@0.5.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend allowlisted hatchling.build

Background: Why install scripts are a supply-chain risk →

Vulnerabilities 32 findings
ID CVE Severity Vector Fix available
GHSA-hvrp-rf83-w775 CVE-2026-52870 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L yes
GHSA-jpw9-pfvf-9f58 CVE-2026-52869 high CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:L yes
GHSA-vj7q-gjh5-988w CVE-2026-59950 high yes
PYSEC-2026-3481 CVE-2026-52870 high CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:L/A:L yes
PYSEC-2026-3482 CVE-2026-52869 high CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:L yes
PYSEC-2026-3483 CVE-2026-59950 none yes
GHSA-45hq-cxwh-f6vc CVE-2026-55379 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-4x4j-2g7c-83w6 CVE-2026-55798 medium CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:L/I:L/A:L yes
GHSA-5x94-69rx-g8h2 CVE-2026-54060 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-62p4-gmf7-7g93 CVE-2026-54058 high yes
GHSA-6r8x-57c9-28j4 CVE-2026-59199 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-8v84-f9pq-wr9x CVE-2026-54059 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-9hw9-ch79-4vh6 CVE-2026-59205 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-fj7v-r99m-22gq CVE-2026-59198 medium CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:L yes
GHSA-jjj6-mw9f-p565 CVE-2026-59200 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-pg7v-jwj7-p798 CVE-2026-59203 medium CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:L yes
GHSA-phj9-mv4w-65pm CVE-2026-55380 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
GHSA-vjc4-5qp5-m44j CVE-2026-59204 high yes
GHSA-xj96-63gp-2gmr CVE-2026-59197 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H yes
PYSEC-2026-2253 CVE-2026-54059 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-2254 CVE-2026-54060 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-2255 CVE-2026-55379 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-2256 CVE-2026-55380 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-2257 CVE-2026-55798 medium CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:L/I:L/A:L yes
PYSEC-2026-3451 CVE-2026-59199 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-3452 CVE-2026-59203 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-3453 CVE-2026-59205 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-3454 CVE-2026-59197 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:H yes
PYSEC-2026-3493 CVE-2026-54058 none yes
PYSEC-2026-3494 CVE-2026-59198 medium CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:L yes
PYSEC-2026-3495 CVE-2026-59200 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes
PYSEC-2026-3496 CVE-2026-59204 none yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 63 packages
Packages resolved 63
Stale 2
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 10 exposed · ~444 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
create_interactive_session ~39

Create a new interactive OpenROAD session.

NameTypeReqDescription
command
cwd
env
session_id
NameTypeReqDescription
resultstringyes

No examples provided.

get_session_history ~37

Get command history for an interactive OpenROAD session.

NameTypeReqDescription
limit
search
session_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

get_session_metrics ~19

Get comprehensive metrics for all interactive OpenROAD sessions.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

inspect_interactive_session ~29

Get detailed inspection data for an interactive OpenROAD session.

NameTypeReqDescription
session_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

interactive_openroad_exec ~85

Execute a state-modifying OpenROAD command (set_*, create_*, read_*, write_*, flow commands). Use this for loading designs, running placement/routing, applying constraints, and writing output files. Read-only commands are blocked — use interactive_openroad_query instead.

NameTypeReqDescription
commandstringyes
session_id
timeout_ms
NameTypeReqDescription
resultstringyes

No examples provided.

interactive_openroad_query ~81

Execute a read-only OpenROAD command (report_*, get_*, check_*, sta, help, etc.). Use this for querying design state, generating reports, and inspecting timing. Commands that modify design state are blocked — use interactive_openroad_exec instead.

NameTypeReqDescription
commandstringyes
session_id
timeout_ms
NameTypeReqDescription
resultstringyes

No examples provided.

list_interactive_sessions ~18

List all active interactive OpenROAD sessions.

Input schema present but exposes no named parameters.

NameTypeReqDescription
resultstringyes

No examples provided.

list_report_images ~50

List available report images from ORFS runs organized by stage.

NameTypeReqDescription
designstringyes
platformstringyes
run_slugstringyes
stagestring
NameTypeReqDescription
resultstringyes

No examples provided.

read_report_image ~53

Read a report image and return base64-encoded data with metadata.

NameTypeReqDescription
designstringyes
image_namestringyes
platformstringyes
run_slugstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

terminate_interactive_session ~33

Terminate an interactive OpenROAD session.

NameTypeReqDescription
forceboolean
session_idstringyes
NameTypeReqDescription
resultstringyes

No examples provided.

Common questions

What is the io.github.luarss/openroad-mcp server?

io.github.luarss/openroad-mcp is listed in the public MCP registry as io.github.luarss/openroad-mcp. The OpenROAD MCP server - interactive EDA sessions via Model Context Protocol. This page covers its PyPI package (openroad-mcp).

Is the io.github.luarss/openroad-mcp server safe to use?

io.github.luarss/openroad-mcp scores 52 out of 100 on VerifyMCP. We recorded 32 known advisories against it as of 20 September 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the io.github.luarss/openroad-mcp server expose?

io.github.luarss/openroad-mcp exposes 10 tools: interactive_openroad_query, interactive_openroad_exec, list_interactive_sessions, create_interactive_session, terminate_interactive_session, and 5 more. Their descriptions and schemas cost roughly 444 tokens of context every time the server is loaded.

Is the io.github.luarss/openroad-mcp server still maintained?

io.github.luarss/openroad-mcp is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.