用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/javimosch/open-claw-skills --skill mcp-client命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | mcp-client |
| version | 1.0.0 |
| description | Model Context Protocol (MCP) client - connect to tools, data sources and services |
| metadata | {"openclaw":{"emoji":"🔌","category":"integration","requires":{"bins":"[Truncated]","pip":"[Truncated]"},"homepage":"https://modelcontextprotocol.io"}} |
Implementation of the Model Context Protocol (MCP) client for connecting to tools and data sources.
# Install Python dependencies (requests is the only required dependency)
pip install requests
.\mcp.ps1 -Action connect -ServerUrl "https://mcp-server.com" -ApiKey "your-key"
.\mcp.ps1 -Action tools -ServerUrl "https://mcp-server.com"
.\mcp.ps1 -Action call -ServerUrl "https://mcp-server.com" -ToolName "search" -Arguments '{"query": "AI agents"}'
.\mcp.ps1 -Action resources -ServerUrl "https://mcp-server.com"
.\mcp.ps1 -Action read -ServerUrl "https://mcp-server.com" -ResourceUri "file:///data/config.json"
POST /mcp/connect - Connect to server
GET /mcp/tools - List available tools
POST /mcp/call - Invoke a tool
GET /mcp/resources - List resources
GET /mcp/read - Read resource
GET /mcp/prompts - List prompt templates
from mcp_client import MCPClient
client = MCPClient("https://mcp-server.com", api_key="key")
# List tools
tools = client.list_tools()
print(tools)
# Call tool
result = client.call_tool("search", {"query": "quantum"})
print(result)
# Read resource
data = client.read_resource("file:///config.json")
print(data)
The MCP protocol allows file:///path URIs to read files from the server. Only connect to trusted MCP servers. A malicious server could exfiltrate sensitive files.
Review what tools/resources are available before using
Python 3.8+
requests library
MIT