Install MCP is a meta-MCP server that lets AI agents install, configure, and manage other MCP servers on your behalf. Rather than manually editing JSON or using complex command-line installations, you can simply ask your AI assistant to handle everything.
Our installer automatically sets up uv
(the fast Python package manager) and configures everything for you.
curl -sSL https://raw.githubusercontent.com/ddfourtwo/install-mcp/main/install.sh | bash
powershell -c "irm https://raw.githubusercontent.com/ddfourtwo/install-mcp/main/install.ps1 | iex"
uv
if not present (blazing fast Python package manager)uv
to your PATH permanentlyuvx
for instant startupAfter installation:
Once installed, just ask your AI assistant:
"Install the GitHub MCP server for me"
"Can you set up the Slack MCP server?"
"I need the filesystem MCP server installed"
"Show me all my installed MCP servers"
"Export my MCP setup so I can share it"
"Configure the GitHub server in all my MCP clients"
"Collect the API key for the OpenAI server"
"Update the GitHub token for my GitHub MCP server"
Install MCP acts as a package manager for MCP servers:
~/mcp-servers/
├── install-mcp/ # This meta-server
├── mcp-servers-config.json # Central configuration
├── .env # Central secrets (secure)
├── github/ # Example: GitHub MCP server
├── slack/ # Example: Slack MCP server
└── ... # Other installed servers
Your AI assistant can use these tools:
Command | Description |
---|---|
list_mcp_servers() |
Show all installed servers and their status |
execute_in_mcp_directory() |
Run installation commands |
collect_secrets() |
Securely collect API keys via web interface |
add_server_to_central_config() |
Add server to central configuration |
configure_mcp_clients() |
Apply config to all MCP clients |
export_mcp_setup() |
Export complete setup for sharing |
Install MCP can handle various MCP server types:
# Servers published to npm
Command: npx -y @organization/package-name@latest
# Servers with package.json
1. Clone repository
2. Run npm install
3. Run npm build (if needed)
4. Configure with: node path/to/server.js
# Servers with requirements.txt
1. Clone repository
2. Run pip install -r requirements.txt
3. Configure with: python3 path/to/server.py
# Standalone binaries
Configure with direct path to executable
~/mcp-servers/install-mcp/
python3 --version
~/mcp-servers/.env
GITHUB_GITHUB_TOKEN
)ls -la ~/mcp-servers/.env
(should be -rw-------
)list_mcp_servers()
to check current statusTo add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "install-mcp" '{"command":"python3","args":["~/mcp-servers/install-mcp/server/meta_mcp.py"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"install-mcp": {
"command": "python3",
"args": [
"~/mcp-servers/install-mcp/server/meta_mcp.py"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"install-mcp": {
"command": "python3",
"args": [
"~/mcp-servers/install-mcp/server/meta_mcp.py"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect