经 AI Skill Hub 精选评估,简例MCP序回 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
简例MCP序回给LLMs得法给编索得法。简例MCP序回给编索给编索。简例MCP序回给编索给编索。
简例MCP序回 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
简例MCP序回给LLMs得法给编索得法。简例MCP序回给编索给编索。简例MCP序回给编索给编索。
简例MCP序回 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/Cognitohazard/ltspice-mcp
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"--mcp--": {
"command": "npx",
"args": ["-y", "ltspice-mcp"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 简例MCP序回 执行以下任务... Claude: [自动调用 简例MCP序回 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"__mcp__": {
"command": "npx",
"args": ["-y", "ltspice-mcp"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Work in progress. Core functionality is usable but expect rough edges, missing features, and breaking changes.
MCP server that exposes LTspice circuit simulation to LLMs via the Model Context Protocol. Create netlists, edit schematics, run simulations, and analyze results through MCP tool calls.
Built on the low-level mcp.server.lowlevel.Server API with spicelib for simulator interfacing and result parsing.
```
Any Python package installer works — pick whichever you already use.
```bash
uv tool install ltspice-mcp
pip install ltspice-mcp
git clone https://github.com/Cognitohazard/ltspice-mcp.git
cd ltspice-mcp
uv sync # or: pip install -e .
pip install -e . --group dev pytest tests/ -v pyright ltspice-mcp ```
```bash cp ltspice-mcp.example.toml ltspice-mcp.toml
Every client below uses the same JSON snippet — only the config file path differs. Paste this into the client's MCP config file:
{
"mcpServers": {
"ltspice": {
"command": "ltspice-mcp",
"args": []
}
}
}
If ltspice-mcp isn't on the client's PATH (common on macOS GUI apps), use the absolute path — find it with which ltspice-mcp (Linux/macOS) or where ltspice-mcp (Windows).
On WSL, LTspice.exe runs via Windows interop (not Wine), so spicelib can't auto-detect it across the WSL boundary. Set the Windows-side path explicitly in ltspice-mcp.toml:
[simulator]
path = "/mnt/c/Program Files/ADI/LTspice/LTspice.exe"
Simulation output is automatically redirected to a Windows temp directory. LTspice writes SQLite .db files alongside results, and these fail on UNC paths (\\wsl.localhost\...), which causes .MEAS data to be lost.
Copy ltspice-mcp.example.toml to ltspice-mcp.toml and edit. All settings can be overridden with LTSPICE_MCP_ prefixed environment variables (highest precedence). The config file path itself can be set with --config PATH or the LTSPICE_MCP_CONFIG env var.
[simulator]
default = "ltspice" # ltspice, ngspice, qspice, xyce (null = auto-detect)
path = "" # Explicit executable path (required on WSL)
[security]
allowed_paths = ["."] # Sandbox: only these directories are accessible
[simulation]
max_parallel = 4 # Concurrent simulation limit
timeout = 300.0 # Default timeout in seconds
[analysis]
max_points = 10000 # Max waveform data points per trace
[plotting]
dpi = 150 # Plot resolution
style = "seaborn-v0_8-darkgrid" # Matplotlib style
[schematic]
symbol_paths = [] # Custom .asy symbol paths (auto-detected on Windows/WSL)
[logging]
level = "INFO" # DEBUG, INFO, WARNING, ERROR, CRITICAL
简例MCP序回给编索给编索。简例MCP序回给编索给编索。简例MCP序回给编索给编索。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
⚠️ GPL 3.0 — 强 Copyleft,衍生作品须开源,含专利保护条款,不可闭源使用。
AI Skill Hub 点评:简例MCP序回 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | ltspice-mcp |
| 原始描述 | 开源MCP工具:MCP server giving LLMs the ability to design, simulate, and analyze SPICE circui。⭐13 · Python |
| Topics | mcpai-toolsanthropiccircuit-designcircuit-simulationcircuit-simulatorpython |
| GitHub | https://github.com/Cognitohazard/ltspice-mcp |
| License | GPL-3.0 |
| 语言 | Python |
收录时间:2026-06-08 · 更新时间:2026-06-08 · License:GPL-3.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端