How to Use the CyberArk Privilege Cloud MCP in LangChain

Q: How do I setup the CyberArk Privilege Cloud MCP Server in LangChain?

Install langchain-mcp-adapters via pip and initialize the MultiServerMCPClient with your Vinkius HTTP endpoint. Pass the tools retrieved from client.gettools() directly to your agent constructor to start executing vault operations.

Q: How does LangSmith help audit CyberArk Privilege Cloud operations inside LangChain?

LangSmith logs every single execution of tools like retrievepassword or deleteaccount. You get full visibility into the exact parameters passed, execution latency, and the specific justification strings submitted by the agent.

Run multi-step security chains to manage privileged access using LangChain and this CyberArk Privilege Cloud integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CyberArk Privilege Cloud MCP to LangChain

Create your Vinkius account to connect CyberArk Privilege Cloud 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 CyberArk Privilege Cloud with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate PAM platforms inside LangChain loops

The `add_account` tool provisions a new privileged account into a Vault Safe using a precise Platform ID. Your LangChain agent evaluates the target environment, selects the correct Windows or Unix platform template, and writes the credentials directly to the secure Vault. LangSmith tracks the latency and token usage of this mapping step in real time. If the platform template fails validation, the chain halts before executing downstream steps, preventing orphaned accounts in your target infrastructure.

Secure password checkout with LangChain tracing

The `retrieve_password` tool pulls clear-text credentials from the vault while requiring a mandatory justification string. In a LangChain ReAct loop, the agent prompts the user for a business reason, validates it against policy, and executes the checkout. Because this endpoint triggers high-severity SIEM alerts, the framework records the exact justification and tool inputs inside your LangSmith traces. This ensures every automated password pull has a clear, audited paper trail.

Kill compromised PSM sessions via MCP Server

The `terminate_session` tool forcibly closes active Privileged Session Manager sessions when anomalous behavior is detected. When linked to an incident response chain, your agent checks active sessions via `list_users` and immediately kills unauthorized connections. The MCP Server acts as an immediate circuit breaker during active compromises. By combining these tools with LangChain's multi-step decision logic, your agent neutralizes threats without waiting for human intervention.

Setup guide

Set up CyberArk Privilege Cloud 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 CyberArk Privilege Cloud 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({
    "cyberark-privilege-cloud-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 CyberArk Privilege Cloud 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 CyberArk. 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 CyberArk Privilege Cloud 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 CyberArk Privilege Cloud MCP in LangChain

Install `langchain-mcp-adapters` via pip and initialize the `MultiServerMCPClient` with your Vinkius HTTP endpoint. Pass the tools retrieved from `client.get_tools()` directly to your agent constructor to start executing vault operations.

Yes, because LangChain uses composable chains, the output of `list_safes` can feed directly into `add_account`. The agent decides which safe to target based on the live metadata returned in the previous chain link.

LangSmith logs every single execution of tools like `retrieve_password` or `delete_account`. You get full visibility into the exact parameters passed, execution latency, and the specific justification strings submitted by the agent.

The LangChain execution chain catches the API error, allowing your agent to log the failure or attempt an alternative path. This prevents your automation scripts from crashing when encountering locked accounts or permission errors.

This server runs inside an ephemeral, zero-trust V8 isolate sandbox on Vinkius. Clear-text passwords retrieved via `retrieve_password` are passed directly to your runtime environment and are never cached or stored on our servers.

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