菜单
Install a pre-configured MCP config file into various agent tool directories. Use when the user wants to install an mcp_config.json into Windsurf, Claude Code, OpenCode, Antigravity, Devin, Codex, or a custom agent path. It handles merging with existing configurations.
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。
基于 SOC 职业分类
Scaffold a complete agent-package project with all config files, Docker infrastructure, MCP server, A2A agent, and API client stubs. Use when creating a brand-new agent-package from scratch, bootstrapping a new MCP/agent/api-client project, or when the user says "create a new agent package". This delegates domain-specific implementation to existing skills (api-client-builder, mcp- builder, agent-builder, skill-graph-builder). Do NOT use for modifying an existing agent package — use the individual skills directly.
Browser automation CLI for AI agents using the agent-browser tool. Use when the user needs to interact with websites including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Guide for building scalable Pydantic AI agents. Use this skill when the user wants to create a new agent package or modify an existing agent's architecture, to ensure it follows the standardized agent patterns using `agent-utilities`.
The `agent-spawner` skill provides the ability to dynamically create a new Pydantic AI agent configured with an external MCP server toolkit. This is extremely useful when an agent wants to spin up a sub-agent with specialized tools defined in an `mcp_config.json`, and interact with that agent immediately without modifying the parent agent's state or toolset.
Consolidated skill for managing, dispatching, and orchestrating other agents via the agent-manager CLI, as well as workflows for A2A communication, orchestration, and parallel subagent dispatch.
Use when executing implementation plans with independent tasks in the current session
| name | mcp-installer |
| domain | agent-tools |
| skill_type | skill |
| description | Install a pre-configured MCP config file into various agent tool directories. Use when the user wants to install an mcp_config.json into Windsurf, Claude Code, OpenCode, Antigravity, Devin, Codex, or a custom agent path. It handles merging with existing configurations. |
| license | MIT |
| tags | ["mcp","installer","deployment","agent-tools","config"] |
| metadata | {"version":"1.2.1","author":"Genius"} |
This skill allows you to install and merge a pre-configured mcp_config.json into the configuration files of various agent development tools.
~/.codeium/windsurf/mcp_config.json~/.claude.json (Claude Code)~/.config/Claude/claude_desktop_config.json (Linux XDG path)~/.config/opencode/mcp.json~/.gemini/antigravity/mcp_config.json~/.config/agent-utilities/mcp_config.json~/.config/devin/mcp_config.json~/.codex/mcp_config.jsonInstall an mcp_config.json file into a target tool's configuration directory. It merges the mcpServers object so you don't lose your existing configuration, unless you specify --force.
--config: The path to the source mcp_config.json file you want to install.--tool: The target tool to install into (windsurf, claude, claude-desktop, opencode, antigravity, devin, codex).--path: (Optional) Explicit custom path to the target configuration file.--force: (Optional) Overwrite existing configuration entirely rather than merging mcpServers.# Install into Windsurf
python scripts/install.py --config ./my_mcp_config.json --tool windsurf
# Install into Antigravity (Agent Utilities XDG dir)
python scripts/install.py --config ./mcp_config.json --tool antigravity
# Install into Claude Code
python scripts/install.py --config /path/to/mcp_config.json --tool claude
# Install into a custom configuration file explicitly
python scripts/install.py --config ./mcp_config.json --path ~/.my_custom_agent/mcp.json