// SCAN REPORT

Mcp Openroad

12 tools. 11 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 21 Sept 2026

11 can modify or destroy data

1 read-only

12 tools total

Community server · catalogue entry checked 21/09/2026 · full schemas captured for 12 of 12 tools

How to control Mcp Openroad ↓

TOOL MAP

What Mcp Openroad exposes to your agents

Read (1) Write / Execute (0) Destructive / Financial (1)

Running more than one server? Check your whole stack →

CONTEXT-WINDOW COST

What Mcp Openroad costs in tokens

2,064 tokens of tool definitions, loaded on every request

1.0% of a 200k context window

287 heaviest tool: openroad_pnr

Full per-tool breakdown → Model it in the token calculator →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Openroad tools

Destructive · High openroad_power Reports power (total/internal/switching/leakage watts plus per-group breakdown) for a placed or routed DEF via OpenSTA report_power. True IR

11 of Mcp Openroad's 12 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Openroad

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Openroad, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "openroad_power": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Cap read operations

{
  "openroad_eval": {
    "limits": [
      {
        "counter": "openroad_eval_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Mcp Openroad — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP OPENROAD →

Instant setup, no code required.

FULL CATALOGUE

All 12 Mcp Openroad tools

DESTRUCTIVE 1 tools

Destructive openroad_power Reports power (total/internal/switching/leakage watts plus per-group breakdown) for a placed or routed DEF via

READ 1 tools

Read openroad_eval Evaluates a Tcl snippet in a fresh stateless OpenROAD session and returns capped stdout. Include any read_lef/

OTHER 10 tools

Other openroad_cts Runs clock tree synthesis (CTS) on a placed DEF file, reporting inserted clock buffers/nets and post-CTS timin Other openroad_detail_route Runs detailed routing on a globally-routed DEF file and reports DRC issue counts with samples. Completes even Other openroad_floorplan Initializes ASIC floorplan boundaries, core/die sizing, and I/O pin placement using OpenROAD, generating a flo Other openroad_pdn Inserts a stdcell power grid (followpins rails + upper-layer straps). Sky130 only. The step tool takes a place Other openroad_place Performs standard cell global analytical placement (RePLace) and legalized detailed placement (DPL) on a floor Other openroad_pnr Performs end-to-end automated digital ASIC physical design (floorplanning, placement, routing, and static timi Other openroad_route Performs global routing (FastRoute) on a placed DEF file, reporting wirelength estimates. Use openroad_detail_ Other openroad_sta Performs static timing analysis using OpenSTA on placed or routed DEF files, reporting Worst Negative Slack (W Other openroad_sta_corners Runs static timing analysis across multiple Liberty corners (one .lib per corner) on a DEF file, reporting per Other openroad_toolchain_info Returns active container/host runtime and version information for OpenROAD, OpenSTA, and supported platform PD

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Openroad

Can an AI agent delete data through the Mcp Openroad MCP server? +

Yes. The Mcp Openroad server exposes 1 destructive tools including openroad_power. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How many tools does the Mcp Openroad MCP server expose? +

12 tools across 3 categories: Destructive, Other, Read. 1 are read-only. 11 can modify, create, or delete data.

How do I enforce a policy on Mcp Openroad? +

Register the Mcp Openroad MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Mcp Openroad tool call.

Deterministic rules across all 12 Mcp Openroad tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP OPENROAD →

Instant setup, no code required.

12 Mcp Openroad tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from Mcp Openroad's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →