How to Use the Frontegg MCP in LangChain

Q: How do I connect the Frontegg MCP Server to a LangChain agent?

Install langchain-mcp-adapters and configure a MultiServerMCPClient. Pass your endpoint URL to client.gettools() and inject that list directly into your ReAct agent setup.

Q: Does the agent maintain context between tool calls?

The client is stateless by default. You need to use client.session() if you want the agent to remember a tenant ID between separate pipeline runs.

Q: How do I handle multi-step provisioning in LangChain with Frontegg?

Build a sequential pipeline where the output of createtenant feeds into the input of createuser. The framework automatically parses the new tenant ID and passes it to the next step.

Build multi-step identity workflows by connecting Frontegg to your LangChain agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Frontegg MCP to LangChain

Create your Vinkius account to connect Frontegg 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 Frontegg with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Frontegg MCP Server tools.

The `list_tenants` and `create_user` tools turn identity management into a sequence of agent-driven decisions. Your LangChain agent can find an account, check its state with `get_tenant_details`, and immediately provision a new admin if the pipeline requires it. You get full visibility into these operations through LangSmith. Every API call latency and token usage metric logs automatically while your pipeline executes complex B2B provisioning tasks.

Automate tenant offboarding.

The `delete_tenant` tool gives your application direct control over account teardowns. Instead of clicking through a dashboard, your ReAct agent evaluates a termination request, verifies the target account, and wipes it entirely. This MCP integration lets you string actions together. You can run `list_users` to notify remaining admins before the final deletion sequence triggers. The agent decides the exact execution order based on the intermediate outputs of your previous steps.

Audit permissions across accounts.

The `list_permissions` and `list_system_roles` tools let you build custom security sweep chains. Your agent pulls the available roles and maps them against active accounts to spot over-privileged users. If it finds an anomaly, the agent can trigger `delete_user` to revoke access immediately. You define the reasoning logic, and the tools handle the actual state changes in your Frontegg environment.

Setup guide

Set up Frontegg 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 Frontegg 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({
    "frontegg-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 Frontegg 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 Frontegg. 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 Frontegg 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 Frontegg MCP in LangChain

Install `langchain-mcp-adapters` and configure a `MultiServerMCPClient`. Pass your endpoint URL to `client.get_tools()` and inject that list directly into your ReAct agent setup.

Yes, through LangSmith tracing. Every tool execution logs the exact inputs, outputs, and latency metrics for your identity operations.

The client is stateless by default. You need to use `client.session()` if you want the agent to remember a tenant ID between separate pipeline runs.

Build a sequential pipeline where the output of `create_tenant` feeds into the input of `create_user`. The framework automatically parses the new tenant ID and passes it to the next step.

Vinkius routes your API traffic through an ephemeral V8 Isolate Sandbox. When your agent pulls email addresses or role assignments via `get_user_details`, the sandbox destroys itself immediately after the handoff. Nothing persists on our infrastructure.

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