DataDome MCP Server for LangChain 10 tools — connect in under 2 minutes
LangChain is the leading Python framework for composable LLM applications. Connect DataDome through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
async with MultiServerMCPClient({
"datadome": {
"transport": "streamable_http",
"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
}
}) as client:
tools = client.get_tools()
agent = create_react_agent(
ChatOpenAI(model="gpt-4o"),
tools,
)
response = await agent.ainvoke({
"messages": [{
"role": "user",
"content": "Using DataDome, show me what tools are available.",
}]
})
print(response["messages"][-1].content)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About DataDome MCP Server
Integrate DataDome, the leading bot protection and fraud prevention solution, directly into your AI workflow. Monitor your web and mobile applications for automated threats, audit protected endpoints, and track real-time protection statistics using natural language.
LangChain's ecosystem of 500+ components combines seamlessly with DataDome through native MCP adapters. Connect 10 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.
What you can do
- Threat Monitoring — List and retrieve full details for recently detected bot threats and suspicious activities.
- Endpoint Auditing — Monitor the health and protection status of all your integrated web and mobile endpoints.
- Protection Insights — Access real-time statistics and dashboard data on bot traffic and mitigation.
- Rule Management — List custom bot rules and explore bypass tokens configured in your account.
The DataDome MCP Server exposes 10 tools through the Vinkius. Connect it to LangChain in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect DataDome to LangChain via MCP
Follow these steps to integrate the DataDome MCP Server with LangChain.
Install dependencies
Run pip install langchain langchain-mcp-adapters langgraph langchain-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save the code and run python agent.py
Explore tools
The agent discovers 10 tools from DataDome via MCP
Why Use LangChain with the DataDome MCP Server
LangChain provides unique advantages when paired with DataDome through the Model Context Protocol.
The largest ecosystem of integrations, chains, and agents. combine DataDome MCP tools with 500+ LangChain components
Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step
LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging
Memory and conversation persistence let agents maintain context across DataDome queries for multi-turn workflows
DataDome + LangChain Use Cases
Practical scenarios where LangChain combined with the DataDome MCP Server delivers measurable value.
RAG with live data: combine DataDome tool results with vector store retrievals for answers grounded in both real-time and historical data
Autonomous research agents: LangChain agents query DataDome, synthesize findings, and generate comprehensive research reports
Multi-tool orchestration: chain DataDome tools with web scrapers, databases, and calculators in a single agent run
Production monitoring: use LangSmith to trace every DataDome tool call, measure latency, and optimize your agent's performance
DataDome MCP Tools for LangChain (10)
These 10 tools become available when you connect DataDome to LangChain via MCP:
get_bot_traffic_summary
Returns a summary of traffic from "Good Bots" (e.g., search engines) versus "Bad Bots" (e.g., scrapers, scrapers) and their impact on total traffic. Get a summary of bot traffic categorized by type
get_endpoint_health
Returns latency metrics, error rates, and the current operational state of the DataDome integration for the endpoint. Check the health status of a specific protected endpoint
get_protection_stats
Returns real-time counts of allowed vs. blocked requests, captcha pass rates, and identified bot categories. Retrieve real-time protection statistics and dashboard data
get_threat_details
Resolves detailed request headers, behavioral patterns, and the specific detection logic triggered. Get full technical details for a specific threat ID
list_access_logs
Returns a stream of recent requests processed by DataDome, including bot scores, decision outcomes, and geo-location data. List recent access logs filtered by DataDome
list_custom_bot_rules
Returns a list of custom bot detection rules, including match criteria (IP, User-Agent, etc.), action (allow/block/captcha), and rule priority. List all custom blocking and allowing rules
list_protected_applications
Returns application names, API keys (masked), and the types of protection enabled (Web/Mobile/API). List all applications (mobile, web) integrated with DataDome
list_protected_endpoints
Returns metadata including endpoint URLs, protection status, and associated application IDs. List all endpoints protected by DataDome
list_recent_threats
Returns a list of recent security incidents including threat types (e.g., scraping, credential stuffing), origin IPs, and detection timestamps. List recently detected bot threats and suspicious activities
search_threats_by_type
Matches the provided threat type against recent incidents to isolate specific attack vectors like "scraper" or "crawler". Search for recent threats by threat type keyword
Example Prompts for DataDome in LangChain
Ready-to-use prompts you can give your LangChain agent to start working with DataDome immediately.
"List all recent bot threats detected in the last 24 hours."
"Check the health status of our main 'Mobile App' endpoint."
"What is the summary of bot traffic for this week?"
Troubleshooting DataDome MCP Server with LangChain
Common issues when connecting DataDome to LangChain through the Vinkius, and how to resolve them.
MultiServerMCPClient not found
pip install langchain-mcp-adaptersDataDome + LangChain FAQ
Common questions about integrating DataDome MCP Server with LangChain.
How does LangChain connect to MCP servers?
langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.Which LangChain agent types work with MCP?
Can I trace MCP tool calls in LangSmith?
Connect DataDome with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect DataDome to LangChain
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.