mcp-kicad-cli
Enables KiCad CLI automation via MCP, providing tools for ERC, DRC, BOM export, netlist export, Gerbers, drill files, STEP, IPC-2581, and GLB output.
README
mcp-kicad-cli
Model Context Protocol server for KiCad CLI automation.
mcp-kicad-cli exposes KiCad's command-line tooling to MCP clients for ERC, DRC, BOM export, netlist export, Gerbers, drill files, STEP, IPC-2581, and GLB output. It is local-first: no cloud API key is required, but KiCad must be installed on the machine running the server.
[!NOTE] This is an alpha extraction from the SpectraSynq K1 hardware automation stack. It wraps KiCad CLI commands; it does not bundle KiCad or board design files.
Quickstart
python3 -m venv .venv
. .venv/bin/activate
python -m pip install -e ".[dev]"
pytest
Verify KiCad CLI is available:
kicad-cli version
Run the server:
export KICAD_CLI="$(command -v kicad-cli)"
mcp-kicad-cli
Honest terminal demo
After install, this copy-paste check exercises the package through the same command runner used by the MCP tool:
python - <<'PY'
from mcp_kicad_cli.server import version
print(version()["stdout"].strip())
PY
Expected output is your installed KiCad CLI version, for example 9.0.6.
MCP client config
After installing the package in the Python environment used by your MCP client, add:
{
"mcpServers": {
"kicad-cli": {
"command": "mcp-kicad-cli",
"args": [],
"env": {
"KICAD_CLI": "/opt/homebrew/bin/kicad-cli"
}
}
}
}
See examples/claude_desktop_config.json.
Tools
version()— return the installed KiCad CLI version.sch_erc(schematic, out="erc.json", format="json", exit_code_violations=True)— run ERC on a.kicad_sch.sch_export_bom(schematic, out_csv="bom.csv", fields="*")— export a CSV BOM.sch_export_netlist(schematic, out_net="project.net", fmt="kicadsexpr")— export a schematic netlist.pcb_drc(board, out="drc.json", format="json", exit_code_violations=True)— run DRC on a.kicad_pcb.pcb_export_gerbers(board, out_dir="fab/gerbers")— export Gerbers.pcb_export_drill(board, out_dir="fab/drill")— export drill files.pcb_export_step(board, out_file="mechanical/board.step")— export STEP.pcb_export_ipc2581(board, out_file="fab/board.ipc")— export IPC-2581.pcb_export_glb(board, out_file="mechanical/board.glb")— export GLB.
KiCad returns exit code 5 when violations are found; DRC/ERC wrappers treat 0 and 5 as command-level success and report the violation counts in summary when JSON output exists.
Provenance
Extracted from SpectraSynq/K1.hardware commit 9e0b80beec0840162d3c3946f38c5c83af259790; see docs/provenance.md.
This repo is now the canonical home for the KiCad CLI MCP server.
License
Apache-2.0 — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.