How to Use the Keycloak MCP in CrewAI

Q: How do CrewAI agents collaborate to manage Keycloak roles?

One CrewAI agent can use listroles to find existing permissions, while a second agent uses createrole to add missing ones, sharing state through the crew's memory.

Q: Can I limit which Keycloak tools a CrewAI agent can access?

Yes. Use MCPServerHTTP with a toolfilter in your CrewAI setup to restrict agents to read-only tools like getuser, blocking destructive actions like deleterealm.

Q: How do I connect a CrewAI agent team to my Keycloak MCP Server?

Pass your Vinkius MCP Server URL directly into the mcps list of your CrewAI agents. The framework automatically registers the 34 management tools.

Run collaborative CrewAI agent teams to monitor Keycloak logs, manage user groups, and automate security operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Keycloak MCP to CrewAI

Create your Vinkius account to connect Keycloak 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 Keycloak with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent security monitoring and response

Stop relying on one script to manage Keycloak security in your CrewAI setup. With CrewAI, you can use this MCP Server to set up a monitoring agent that scans `list_admin_events` and a security agent that responds to anomalies by calling `logout_all_users` instantly. These specialized CrewAI agents share memory and collaborate on Keycloak threats. If the CrewAI monitor agent spots a suspicious pattern, it passes the context to the responder, who can restrict Keycloak access by running `update_user` to disable the account.

Autonomous client audits and cleanup

Unused Keycloak clients are a massive security risk for CrewAI deployments, but this MCP Server makes cleanup simple. Your CrewAI auditor agent can run `list_clients` to gather all active client configurations, while a moderator agent evaluates their usage and flags stale entries. Once identified, the CrewAI team can coordinate to run `delete_client` on expired Keycloak test environments. This keeps your production Keycloak environment clean without CrewAI security teams spending hours auditing lists manually.

Automated role and group provisioning teams

Setting up complex Keycloak organizational structures with CrewAI requires intense coordination. A CrewAI planning agent can outline the Keycloak hierarchy, while a provisioning agent executes `create_group` and `create_role` to build the setup. They verify their own work by calling `list_user_groups` to ensure users are placed in the correct Keycloak security boundaries. The entire CrewAI process runs autonomously, matching your actual company structure in Keycloak.

Setup guide

Set up Keycloak 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 Keycloak tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Keycloak 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 Keycloak. 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 Keycloak 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 Keycloak MCP in CrewAI

One CrewAI agent can use `list_roles` to find existing permissions, while a second agent uses `create_role` to add missing ones, sharing state through the crew's memory.

Yes. Use `MCPServerHTTP` with a `tool_filter` in your CrewAI setup to restrict agents to read-only tools like `get_user`, blocking destructive actions like `delete_realm`.

Pass your Vinkius MCP Server URL directly into the `mcps` list of your CrewAI agents. The framework automatically registers the 34 management tools.

Yes. A support-focused CrewAI agent can take a user request, verify their identity details, and call `reset_user_password` to restore access automatically.

This MCP Server runs in a zero-trust V8 isolate sandbox. Your user database records, group structures, and admin event logs are processed ephemerally and never stored on Vinkius.

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