index

A guide to connecting KiCad MCP Pro, a service that gives AI agents tools for inspecting and checking circuit-board designs, to different coding assistants.

In plain words
What is it for?
Use it to choose a supported assistant, follow installation steps, run diagnostics, and understand support for board review, design-rule checks, manufacturing export, and simulation.
Why use it?
It shows which assistants support local or remote connections and which setup features are available, reducing trial and error during configuration.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/oaslananka/kicad-mcp-pro/index
Clone the repo
git clone --depth 1 https://github.com/oaslananka/kicad-mcp-pro
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 868 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00868
Opus 5 $0.00000 $0.00434
Sonnet 5 $0.00000 $0.00174
Haiku 4.5 $0.00000 $0.00087

Measured yesterday against content hash 659c2f71b8b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

index scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/index.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KiCad MCP — AI Agent Integration Guide

kiCad-mcp-pro is an MCP server that exposes KiCad PCB design capabilities as tools for AI agents: board inspection, schematic/PCB review, DRC/ERC, DFM, manufacturing export, SPICE simulation, and more.

Supported Agents

Agent Local STDIO Remote HTTP Skills App UI
Claude Code ✅ Supported ✅ Supported ✅ Supported
Codex CLI ✅ Supported ✅ Supported Via AGENTS.md
Gemini CLI ✅ Supported ✅ Supported
OpenCode ✅ Supported ✅ Supported ✅ Plugin
VS Code / Copilot ✅ Supported ✅ Supported Experimental
Cursor ✅ Supported ⚠️ Verify ✅ Supported
Claude Desktop ✅ Supported
.mcpb bundle ✅ Supported ✅ 1-file install
Claude.ai Web ❌ No ✅ Supported Limited
ChatGPT Web ❌ No ✅ Supported ✅ Apps SDK
Antigravity ⚠️ Verify ✅ Supported
Cline ✅ Supported ✅ Supported ✅ Reusable
Windsurf ✅ Supported ✅ Supported
Continue ✅ Supported ✅ Supported
Zed ✅ Supported ✅ Supported

Quick Start

For a client-by-client copy-paste setup overview, see the Quickstart Matrix. For bounded review/build/release tool surfaces, see Progressive-Disclosure Profiles.

# Install
pipx install kicad-mcp-pro

# Run diagnostics
kicad-mcp-pro doctor

# Generate config for your agent
kicad-mcp-pro mcp-config generate --client claude

# Or use the setup wizard
kicad-mcp-pro setup

Architecture Overview

┌─────────────────────────────────────────────────────────┐
│                    AI Agent Host                         │
│  (Claude Code, Codex, Gemini CLI, ChatGPT, etc.)        │
└──────────┬──────────────────────────────────┬───────────┘
           │ STDIO / HTTP                     │ HTTP
           ▼                                  ▼
┌──────────────────────┐         ┌──────────────────────────┐
│  Local KiCad MCP     │         │  Remote KiCad MCP Cloud  │
│  (uvx kicad-mcp-pro) │         │  (Public HTTPS endpoint) │
│  Full tool access    │         │  Read-only tools         │
│  Direct file access  │         │  Upload analysis         │
└──────────────────────┘         └──────────────────────────┘

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 78 lines · 0 tokens per session scan A 659c2f71b8b8

Subscribe to this mod's changes

index is an agent published in the GitHub repository oaslananka/kicad-mcp-pro (62 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 868 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.