Skip to main content
The easiest way to get started is the SafeDep CLI — one command signs you in, sets up your API key, and configures SafeDep protection in every AI coding agent it finds on your machine. If you prefer to set things up manually, instructions for each agent are available below. SafeDep monitors npm, PyPI, and other package registries in real time. It’s invisible when packages are safe — you only see it when it blocks something dangerous.
SafeDep MCP has a free tier. See pricing for details.

​
Quick Start

1

Run the setup command

Run the following command in your terminal. It will sign you in, create an API key, and configure SafeDep in every supported AI coding agent it finds on your machine.
npx @safedep/cli setup mcp install
SafeDep MCP setup via CLI
2

Test the Integration

Verify the setup by asking your coding agent to install a test package. The agent should block it as malicious.Claude using SafeDep MCP

​
Endpoints

EndpointDescription
https://mcp.safedep.io/model-context-protocol/threats/v1/mcpSafeDep MCP endpoint (HTTP)
https://mcp.safedep.io/model-context-protocol/threats/v1/sseLegacy SSE endpoint

​
Authentication

The MCP server requires SafeDep API key based authentication. Following HTTP headers are required:
HeaderDescription
Authorization<API Key>
X-Tenant-IDyour-tenant-domain (e.g. default-team.your-domain.safedep.io)
Your tenant domain is shown in SafeDep Cloud settings after you sign in.

​
Manual Setup

If you’d rather configure things yourself, or your agent isn’t auto-detected by the CLI, here’s how to set up each one manually.
Use claude CLI to add the MCP server to your user settings. This configuration will be available across all Claude Code projects.
claude mcp add -s user --transport http safedep \
  https://mcp.safedep.io/model-context-protocol/threats/v1/mcp \
  --header "Authorization: <API Key>" \
  --header "X-Tenant-ID: <Tenant Domain>"
Add the SafeDep MCP server to your Cursor configuration. Create or edit ~/.cursor/mcp.json in your home directory:
{
  "mcpServers": {
    "safedep": {
      "url": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
Restart Cursor after saving the configuration. You can verify the server connection in Cursor Settings > MCP Servers.See the Cursor MCP documentation for more details.
Add the SafeDep MCP server to your VS Code configuration. Create or edit the user-level mcp.json file for your platform:
PlatformPath
Linux~/.config/Code/User/mcp.json
macOS~/Library/Application Support/Code/User/mcp.json
Windows%APPDATA%\Code\User\mcp.json
{
  "servers": {
    "safedep": {
      "type": "http",
      "url": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
Reload VS Code after saving the configuration.
Add the SafeDep MCP server to your Gemini CLI configuration. Edit ~/.gemini/settings.json in your home directory:
{
  "mcpServers": {
    "safedep": {
      "httpUrl": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
See the Gemini CLI MCP documentation for more details.
Add the SafeDep MCP server to your OpenCode configuration. Create or edit ~/.config/opencode/opencode.json in your home directory:
{
  "mcp": {
    "safedep": {
      "type": "remote",
      "url": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
Add the SafeDep MCP server to your Antigravity configuration. Create or edit ~/.gemini/antigravity/mcp_config.json in your home directory:
{
  "mcpServers": {
    "safedep": {
      "serverUrl": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
Add the SafeDep MCP server to your Codex configuration. Edit ~/.codex/config.toml (or .codex/config.toml in your project root for project-scoped access):
[mcp_servers.safedep]
url = "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp"

[mcp_servers.safedep.env_http_headers]
"Authorization" = "SAFEDEP_API_KEY"
"X-Tenant-ID" = "SAFEDEP_TENANT_ID"
Set the environment variables with your credentials:
export SAFEDEP_API_KEY="<API Key>"
export SAFEDEP_TENANT_ID="<Tenant Domain>"
See the Codex MCP documentation for more details.
Add the SafeDep MCP server to your Windsurf configuration. Create or edit ~/.codeium/windsurf/mcp_config.json in your home directory:
{
  "mcpServers": {
    "safedep": {
      "url": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
See the Windsurf Cascade MCP documentation for more details.
Add the SafeDep MCP server to your Zed configuration. Create or edit ~/.config/zed/settings.json in your home directory.
{
  "context_servers": {
    "safedep": {
      "enabled": true,
      "url": "https://mcp.safedep.io/model-context-protocol/threats/v1/mcp",
      "headers": {
        "Authorization": "<API Key>",
        "X-Tenant-ID": "<Tenant Domain>"
      }
    }
  }
}
See the Zed MCP documentation for more details.

​
Testing

After setting up the MCP server, you can verify the integration is working by asking your coding agent to install one of the following test packages:
PackageEcosystem
safedep-test-pkgnpm
safedep-test-pkgPyPI
These are harmless packages that are marked as malicious in the SafeDep database, specifically meant for testing. Your coding agent should block the installation and warn you about the package being flagged as malicious. For example, try prompting your agent with: 
Install the npm package safedep-test-pkg
If the MCP server is configured correctly, the agent will check the package against SafeDep’s threat intelligence and refuse to install it.