经 AI Skill Hub 精选评估,callmux 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 7.1 分,适合有一定技术背景的用户使用。
callmux 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。
callmux 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/edimuj/callmux
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"callmux": {
"command": "npx",
"args": ["-y", "callmux"]
}
}
}
# 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 callmux 执行以下任务... Claude: [自动调用 callmux 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": {
"callmux": {
"command": "npx",
"args": ["-y", "callmux"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
Hot-reload MCP servers without restarting your agent. Then make it faster: parallel execution, batching, caching, and pipelining for any AI agent.
---
No install needed. Use npx:
npx -y callmux -- npx -y @modelcontextprotocol/server-github
Or install globally:
npm install -g callmux
---
The fastest way to go from zero to configured:
npx -y callmux setup
The wizard detects existing MCP servers, lets you pick from a curated list or add custom ones, auto-discovers tools via probing, configures caching, offers meta-only mode, and attaches to your client (Claude Code, Codex) automatically.
---
Add to ~/.claude.json or project .mcp.json (Claude Code):
{
"mcpServers": {
"github": {
"command": "npx",
"args": ["-y", "callmux", "--", "npx", "-y", "@modelcontextprotocol/server-github"]
}
}
}
Done. Claude now sees all GitHub tools plus the callmux_* meta-tools.
Works with any MCP client: Codex, Claude Desktop, Cursor, Windsurf, and anything that speaks MCP stdio or HTTP. The interactive setup wizard handles configuration for you.
---
Opt-in management endpoints for standalone shared listeners. Read status/config/server state directly, use the TypeScript SDK, or manage servers from the dashboard. Mutations require management bearer auth and persist to a callmux-owned overlay file instead of rewriting your base config.
{
"management": {
"enabled": true,
"auth": {
"mode": "bearer",
"tokens": [{ "id": "admin", "tokenRef": "env:CALLMUX_MANAGEMENT_TOKEN" }]
}
}
}
Define multi-step operations once in config, call them by name from any agent session. Encode team conventions (bug issues always get the bug label), triage workflows (fetch two issues in parallel for comparison), or analysis pipelines (search then analyze). One name, consistent execution, works across all clients.
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。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:callmux 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 | callmux |
| 原始描述 | 开源MCP工具:Multiplexer for MCP tool calls: parallel execution, batching, caching, and pipel。⭐7 · TypeScript |
| Topics | mcpagentsaibatchclaude-mcpcodex-mcptypescript |
| GitHub | https://github.com/edimuj/callmux |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-05-21 · 更新时间:2026-05-22 · License:MIT · 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