How to Use the Descope (Auth Platform) MCP in CrewAI

Deploy autonomous CrewAI teams to monitor, manage, and audit your Descope authentication infrastructure.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Descope (Auth Platform) MCP to CrewAI

Create your Vinkius account to connect Descope (Auth Platform) 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 Descope (Auth Platform) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Tenant Auditing

Assign an inspector agent to scan your environment using `mgmt_list_tenants` and `mgmt_search_users`. The agent pulls every active organization and cross-references user counts against your billing thresholds. A moderator agent reviews the inspector's findings. If it spots dormant accounts, it executes `mgmt_delete_user` to clean up the directory without requiring a human to click through an admin panel.

Multi-Agent Security Operations

Threat response becomes a sequential execution pipeline. When a monitor agent detects suspicious login activity, it alerts a remediation agent that triggers `auth_password_reset` for the compromised accounts. The crew works together to lock down access. Another specialized agent calls `mgmt_update_user` to revoke specific privileges until the actual human owner verifies their identity.

Delegated Auth Support via MCP Server

Help desk tickets get resolved instantly by a support agent armed with `auth_magiclink_verify` and `auth_get_keys`. A user complains about a broken login, and the crew validates their session tokens in the background. If someone gets locked out, the agent validates their identity through a chat interface. It then fires `auth_enchantedlink_signup` to send a secure, clickable login link straight to their verified email address.

Setup guide

Set up Descope (Auth Platform) 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 Descope (Auth Platform) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent Descope (Auth Platform) 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="Descope (Auth Platform) Analyst",
        goal="Access and analyze Descope (Auth Platform) data via MCP.",
        backstory="Expert analyst with direct Descope (Auth Platform) access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Descope (Auth Platform) 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 Descope. 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 Descope (Auth Platform) 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 Descope (Auth Platform) MCP in CrewAI

Pass the Vinkius endpoint directly into the servers array when defining your agent. CrewAI handles the HTTP transport negotiation and exposes all thirty-three tools to the assigned worker.

Import the HTTP server class and configure a tool filter. You give the support agent access to password resets, while only the admin agent gets permission to create new tenants.

CrewAI maintains shared memory across the execution pipeline. The researcher pulls the profile via the user load tool, and the actor agent reads that exact JSON payload from memory to update the roles.

A manager agent delegates tasks perfectly. It orders a worker to run the OAuth exchange and waits for the session token before deciding which downstream agent should handle the authenticated API calls.

We enforce zero-trust architecture. Access keys, OAuth codes, and session JWTs pass through a strictly ephemeral V8 Isolate sandbox. Once the agent receives the token, the execution environment terminates immediately.

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