How to Use the DataDome MCP in Claude Code

Q: How can I use Claude Code to search for specific DataDome threats?

Use the searchthreatsbytype tool. For example: claude mcp call datadome searchthreatsbytype --type="scraper". You can pipe the resulting JSON to jq for filtering.

Q: Can Claude Code pull a list of all custom DataDome rules for my backup script?

Yes. The command claude mcp call datadome listcustombotrules connects to the MCP Server and will dump all your custom rules as a JSON object. You can redirect the output straight to a file.

Q: What's the command to check DataDome bot traffic stats with Claude Code?

It's claude mcp call datadome getbottrafficsummary. This returns a JSON summary of good vs. bad bot traffic, which you can use in any shell script.

Q: Can I see raw access logs?

You can. The listaccesslogs tool streams recent requests processed by DataDome. You can pipe this data to other command-line tools for real-time processing or logging.

Pipe DataDome security events directly into your shell scripts. Use Claude Code and this MCP server to build alerts and run health checks.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DataDome MCP to Claude Code

Create your Vinkius account to connect DataDome to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DataDome with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Integrate Security into CI/CD

Add a DataDome health check to your deployment pipeline. Before deploying, your script can have Claude Code run `get_endpoint_health` against your production API. If latency is high or error rates are up, the script fails the build. You pipe the JSON output directly into `jq` to parse the results and make a decision.

Scriptable Threat Monitoring

Set up a cron job that uses Claude Code to poll for new threats. The script can call `list_recent_threats` every five minutes to check for new incidents. If a new threat with type 'credential stuffing' appears, pipe the output to a script that sends an alert to your on-call system. It's headless monitoring for your terminal, all through one MCP connection.

Headless Audits via this MCP Server

Run security audits from any machine with SSH access. Use Claude Code to call `list_protected_endpoints` and then pipe that list to another script. The second script can then loop through each endpoint, calling `get_protection_stats` to log daily traffic numbers to a CSV file for later analysis. No UI needed.

Setup guide

Set up DataDome MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see datadome-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest DataDome transactions." It will automatically discover and invoke the available DataDome tools.

Terminal

claude mcp add --transport http datadome-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the DataDome MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "datadome-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DataDome. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DataDome now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DataDome MCP in Claude Code

Use the `search_threats_by_type` tool. For example: `claude mcp call datadome search_threats_by_type --type="scraper"`. You can pipe the resulting JSON to `jq` for filtering.

Yes. The command `claude mcp call datadome list_custom_bot_rules` connects to the MCP Server and will dump all your custom rules as a JSON object. You can redirect the output straight to a file.

It's `claude mcp call datadome get_bot_traffic_summary`. This returns a JSON summary of good vs. bad bot traffic, which you can use in any shell script.

You can. The `list_access_logs` tool streams recent requests processed by DataDome. You can pipe this data to other command-line tools for real-time processing or logging.

It's limited to your DataDome account's operational data. This means it can read traffic summaries, threat logs, and endpoint statistics. Your data is processed in an ephemeral sandbox and is never stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript