How to Use the Intruder MCP in LangChain

Q: How does LangChain use the Intruder MCP Server to find security issues?

Your LangChain agent calls listissues to pull live vulnerabilities. It then passes the issue ID to getissue to extract remediation steps and plan a patch.

Q: Can I trace Intruder tool calls from LangChain in LangSmith?

Yes, every call to listscans or gettarget shows up in your LangSmith dashboard. You get full visibility into the exact payloads and latency of your security runs.

Run multi-step security reasoning chains in LangChain to find, audit, and fix your vulnerabilities using the Intruder MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Intruder MCP to LangChain

Create your Vinkius account to connect Intruder to LangChain 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 Intruder with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Intruder scans to code fixes in LangChain

The `list_issues` tool pulls your active vulnerability list directly into your LangChain agent's execution loop. Your agent checks the severity of each issue, filters for critical flaws, and then calls `get_issue` to pull down specific remediation advice. Because LangChain supports multi-step chains, the output of these security tools feeds directly into your code generation prompts. You'll see exactly how the security decision was made because the agent writes a patch, runs tests, and logs the entire trace in LangSmith.

Audit cloud assets with LangChain and MCP

The `list_targets` tool exposes your entire attack surface to your ReAct agents. Your agent maps these targets against active cloud infrastructure using `list_cloud_integrations` to spot untracked assets before they become entry points. If the agent finds an orphaned IP, it triggers `get_target` to analyze its specific tags and history. You get a complete, traceable lineage of your infrastructure security posture directly inside your terminal or CI pipeline.

Automate scan tracking inside LangChain pipelines

The `list_scans` tool lets your LangChain agent track security checks over time. When a build completes, the agent queries the latest run using `get_scan` to verify that the code didn't introduce new security regressions. Should a scan fail or show open critical issues, the agent stops the deployment pipeline. It uses `list_licences` to verify you have the license capacity to spin up a fresh target for isolated debugging before trying again.

Setup guide

Set up Intruder MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Intruder tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "intruder-mcp": {
        "transport": "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,
    )
    result = await agent.ainvoke({
        "messages": "List recent Intruder transactions"
    })
    print(result["messages"][-1].content)

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 Intruder. 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 Intruder 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 Intruder MCP in LangChain

Your LangChain agent calls `list_issues` to pull live vulnerabilities. It then passes the issue ID to `get_issue` to extract remediation steps and plan a patch.

Yes, every call to `list_scans` or `get_target` shows up in your LangSmith dashboard. You get full visibility into the exact payloads and latency of your security runs.

Use LangChain's built-in rate limiters on the MultiServerMCPClient. This prevents your agent from spamming `get_scan` or `list_targets` and hitting API thresholds.

No. Vinkius manages your API token. Your LangChain agent accesses all tools, from `get_account` to `list_teams`, through a single endpoint.

This MCP Server runs in a sandboxed V8 isolate on Vinkius. Your vulnerability issues, target lists, and account keys never persist on our servers, keeping your threat data private.

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