Skip to main content
SafeDep offers a cloud hosted Model Context Protocol (MCP) server for integrating malicious package feeds into AI Agents and IDEs. This integration enables AI Agents to continue working autonomously while protected against malicious open source packages.

​
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)

​
Quick Start

1

Sign-up for SafeDep

Navigate to app.safedep.io and sign up
2

Create API Key

Create an API key for use with the MCP server from your SafeDep Cloud tenant settings
3

Configure MCP Server

Configure the MCP server with your API key and tenant domain in your favorite IDE or AI Agent (see Setup for more details).
4

Test the Integration

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

​
Setup

​
Claude Code

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>"

​
Cursor

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.

​
OpenAI Codex

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.

​
Gemini CLI

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.

​
Windsurf

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.

​
Zed

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.