How to Use the Frontegg MCP in CrewAI

Q: How do I expose Frontegg MCP tools to a CrewAI agent?

Add the server URL to the mcps array when defining your agent. The framework automatically connects, fetches the available tools, and makes them accessible to that specific agent.

Q: Can I restrict which CrewAI agents can delete Frontegg users?

Yes. Use MCPServerHTTP from the crewai.mcp package and apply a tool filter. You can give your auditor agent read-only access and only expose the deletion endpoints to a highly restricted admin agent.

Deploy a CrewAI agent team to autonomously manage Frontegg tenants, audit permissions, and provision B2B users.

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 CrewAI

Create your Vinkius account to connect Frontegg to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI teams for identity ops

Managing enterprise access requires multiple tools, and connecting this MCP Server gives your execution agent the `create_tenant` endpoint to do the actual work. You can build a CrewAI team where one agent monitors inbound onboarding requests and a second agent executes the provisioning. The first agent reads the requirements and decides on the correct role. It passes instructions to the execution agent, which calls the endpoint followed by `create_user`. The shared memory ensures the second agent knows exactly which workspace ID to use.

Autonomous security auditing

You don't need to manually verify role assignments when an auditor agent can run `list_system_roles` and `list_permissions` on a schedule. It pulls the baseline configurations directly from your environment. A secondary analyst agent takes that baseline and compares it against active accounts using `get_user_details`. If it finds a discrepancy between the assigned role and the expected permissions, it can flag the account or even execute `delete_user` to lock it down instantly.

Validating infrastructure health

Before running massive batch operations, a monitor agent can hit `check_environment_status` to verify the API connection is solid. You never want to start a bulk update if the identity provider is dropping requests. Once the green light is given, the crew can pull the full account roster via `list_tenants`. You configure this by passing the MCP Server URL directly into the `mcps` array in your agent definition. The framework handles the HTTP transport under the hood.

Setup guide

Set up Frontegg MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Frontegg tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Frontegg Analyst",
    goal="Access and analyze Frontegg data via MCP.",
    backstory="Expert analyst with direct Frontegg access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Frontegg transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Frontegg Analyst",
        goal="Access and analyze Frontegg data via MCP.",
        backstory="Expert analyst with direct Frontegg access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Frontegg transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Add the server URL to the `mcps` array when defining your agent. The framework automatically connects, fetches the available tools, and makes them accessible to that specific agent.

Yes. Use `MCPServerHTTP` from the `crewai.mcp` package and apply a tool filter. You can give your auditor agent read-only access and only expose the deletion endpoints to a highly restricted admin agent.

Agents share context through CrewAI's memory system. If one agent fetches an account ID, the subsequent agent in the sequence can read that ID to provision a user.

You can connect using stdio, SSE, or Streamable HTTP. The framework handles the underlying protocol based on how you initialize the connection.

The server interacts with sensitive M2M tokens, user metadata, and tenant IDs. Because it runs in a zero-trust sandbox, this information is only held in memory during the active agent session and is destroyed immediately after.

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