mcp-kicad-pcb-inspector
Parse and analyze KiCad PCB files from AI agents — layer stackup, net listing, footprint inventory, DRC violation surfacing, board outline geometry. Curated by Archimedes Market with a verified Trust Report.
README
Verified asset on Archimedes Market. View the full 4-dimension Trust Report (security · quality · license · complexity) and the curated catalog on the asset page.
MCP KiCad PCB Inspector
Parse and analyze KiCad PCB files from AI agents. Surface layer stackup, net counts, footprint inventory, DRC violations, board outline geometry — without launching the KiCad GUI.
Tools
parse_pcb— header info: title, board version, last save, KiCad versionlayer_stackup— copper + dielectric layers with thickness, material, dielectric constantnet_listing— all nets with pad count and routing-completeness flagfootprint_inventory— placed footprints with reference designator, value, layer, BOM-relevant attributesdrc_violations— Design Rule Check violations from the embedded report (if available)board_outline— board outline polygon coordinates + dimensions
What this is for
Design review automation. Pre-fab sanity checks. An agent reviewing a PR that touches PCB files can answer: "what changed in net VDD_3V3?", "are there any DRC violations?", "what's the new footprint count?", without you opening pcbnew.
What this is not
Not a router. Not a placer. Not a synthesis engine. Read-only parse of the saved file. For interactive PCB editing, use KiCad directly.
Quick start
pip install mcp-kicad-pcb-inspector
mcp-kicad-pcb-inspector serve
Typical agent workflow
Agent: "Review the PR diff against board.kicad_pcb"
↓
1. parse_pcb(file="board.kicad_pcb") → identifies KiCad 10.0.1, last saved 2026-05-15
2. layer_stackup(file=...) → confirms 4-layer is unchanged
3. drc_violations(file=...) → 2 new clearance violations on net DATA_BUS
4. Agent flags the violations inline in PR review
License
MIT.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。