Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
配置和管理 MCP 服务器,实现 AI 调用外部工具如视觉理解和网络搜索的能力。
配置和管理 MCP 服务器,实现 AI 调用外部工具如视觉理解和网络搜索的能力。
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
本技能用于配置和管理 MCP (Model Context Protocol) 服务器,让 AI 能够调用外部工具。
npm install -g clawhub 确保 uvx 可用: which uvx # 如果没有: curl -LsSf https://astral.sh/uv/install.sh | sh
mkdir -p ~/.config/mcporter
{ "mcpServers": { "MiniMax": { "type": "stdio", "command": "uvx", "args": ["minimax-coding-plan-mcp"], "env": { "MINIMAX_API_KEY": "你的API密钥", "MINIMAX_MCP_BASE_PATH": "/tmp/mcporter-output", "MINIMAX_API_HOST": "https://api.minimaxi.com" } } } } 保存到 ~/.config/mcporter/mcporter.json
npx mcporter --config ~/.config/mcporter/mcporter.json list 成功会显示: ✔ Listed 1 server (1 healthy)
npx mcporter --config ~/.config/mcporter/mcporter.json call MiniMax.understand_image \ "prompt: 描述图片内容" \ "image_source: /path/to/image.jpg"
npx mcporter --config ~/.config/mcporter/mcporter.json call MiniMax.web_search \ "query: 搜索内容"
MCP 包名功能minimax-coding-plan-mcp视觉理解、网络搜索linear-mcpLinear 项目管理filesystem-mcp文件系统操作github-mcpGitHub 操作
检查 API Key 是否正确 检查网络连接 确认 MCP 包名正确
查看可用参数: npx mcporter list <服务器名> --schema
确保目录存在 确保有写入权限 最后更新: 2026-02-24
Code helpers, APIs, CLIs, browser automation, testing, and developer operations.
Largest current source with strong distribution and engagement signals.