MCP工具 是 AI Skill Hub 本期精选MCP工具之一。综合评分 7.5 分,整体质量较高。我们推荐使用将其纳入你的 AI 工具库,帮助提升工作效率。
MCP工具 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。
MCP工具 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/thomaswitt/mcp-agents
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp--": {
"command": "npx",
"args": ["-y", "mcp-agents"]
}
}
}
# 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 MCP工具 执行以下任务... Claude: [自动调用 MCP工具 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", "mcp-agents"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
MCP server that wraps AI CLI tools — Claude Code, Antigravity CLI (agy), and Codex CLI — so any MCP client can call them as tools.
$PATH:| CLI | Install |
|---|---|
claude | [Claude Code docs](https://docs.anthropic.com/en/docs/claude-code) |
agy | [Google Antigravity](https://antigravity.google/) |
codex | npm install -g @openai/codex |
Only the CLI you select with --provider needs to be present.
npm install -g mcp-agents
Global install is strongly recommended over npx -y mcp-agents@latest. The npx approach performs a network round-trip on every cold start, which can exceed MCP client connection timeouts and cause "stream disconnected" errors.
Tip: If your project's .mcp.json references mcp-agents, add npm install -g mcp-agents to your setup script (e.g. bin/setup) so new developers get it automatically.
Add entries to your project's .mcp.json (requires npm i -g mcp-agents):
{
"mcpServers": {
"codex": {
"command": "mcp-agents",
"args": ["--provider", "codex"]
},
"gemini": {
"command": "mcp-agents",
"args": ["--provider", "gemini"]
}
}
}
Override codex defaults at server startup:
{
"mcpServers": {
"codex": {
"command": "mcp-agents",
"args": ["--provider", "codex", "--model", "gpt-5.5", "--model_reasoning_effort", "medium"]
}
}
}
The model and effort are fixed at server startup. Per-call model and config arguments sent to the native codex tool are stripped before reaching Codex, so they cannot override the startup defaults.
Because the bridge runs in an isolated Codex home, inherited MCP servers from your normal ~/.codex/config.toml are intentionally unavailable inside bridged Codex sessions.
<details> <summary>Alternative: using npx (slower, not recommended)</summary>
{
"mcpServers": {
"codex": {
"command": "npx",
"args": ["-y", "mcp-agents@latest", "--provider", "codex"]
}
}
}
Warning: npx -y mcp-agents@latest performs a network round-trip on every cold start (~70s), which can exceed MCP client connection timeouts.
</details>
Add two entries to ~/.codex/config.toml — one per provider you want available. Set tool_timeout_sec = 300 to avoid Codex MCP's default 60s per-tool timeout:
[mcp_servers.claude-code]
command = "mcp-agents"
args = ["--provider", "claude"]
tool_timeout_sec = 300
[mcp_servers.gemini]
command = "mcp-agents"
args = ["--provider", "gemini"]
tool_timeout_sec = 300
Then in a Codex session you can call the claude_code or gemini tools, which shell out to the respective CLIs.
高质量MCP工具,易于使用
该工具未明确声明开源协议,商业使用前请联系原作者确认授权范围,避免侵权风险。
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。
经综合评估,MCP工具 在MCP工具赛道中表现稳健,质量良好。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | mcp-agents |
| 原始描述 | 开源MCP工具:MCP server that wraps the Claude Code and Gemini CLI so any MCP client (e.g. cod。⭐4 · JavaScript |
| Topics | mcpjavascriptcli |
| GitHub | https://github.com/thomaswitt/mcp-agents |
| 语言 | JavaScript |
收录时间:2026-05-31 · 更新时间:2026-06-02 · License:未公布 · 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