How do I get Kandji API credentials?

Log in to your Kandji account, navigate to Settings > Access > API Token, and generate a new token. You also need your tenant's API URL.

The API URL is specific to your Kandji instance (e.g., https://yourtenant.api.kandji.io). You can find this in your Kandji API settings.

Can I see remote commands?

Yes, the list_commands tool allows you to retrieve a history of MDM commands sent to your managed devices.

Kandji MCP Server for CrewAI 10 tools — connect in under 2 minutes

Name: Kandji
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 10 Tools Framework

Connect your CrewAI agents to Kandji through the Vinkius — pass the Edge URL in the `mcps` parameter and every Kandji tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Kandji Specialist",
    goal="Help users interact with Kandji effectively",
    backstory=(
        "You are an expert at leveraging Kandji tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Kandji "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 10 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Kandji MCP Server

Empower your AI agents with Kandji's modern Apple MDM platform. This MCP server allows you to list and retrieve device details, manage blueprints and custom apps, track administrative activity, and view system security parameters directly through the Kandji API. Ideal for automating IT operations and fleet security for macOS and iOS.

When paired with CrewAI, Kandji becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Kandji tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

The Kandji MCP Server exposes 10 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Kandji to CrewAI via MCP

Follow these steps to integrate the Kandji MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 10 tools from Kandji

Why Use CrewAI with the Kandji MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Kandji through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Kandji + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Kandji MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Kandji for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Kandji, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Kandji tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Kandji against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Kandji MCP Tools for CrewAI (10)

These 10 tools become available when you connect Kandji to CrewAI via MCP:

get_device

Essential for deep-dive auditing of a specific asset. Retrieves details for a specific device

get_organization

Use to verify account identity. Retrieves details about your Kandji organization

list_activity

Essential for auditing system changes and recent management history. Lists recent management activity

list_auto_apps

Essential for auditing standard software libraries. Lists all Kandji Auto Apps

list_blueprints

Useful for understanding how devices are categorized and configured. Lists all device blueprints

list_commands

g., Lock, Wipe, Restart) sent to managed devices. Useful for auditing remote actions. Lists recent MDM commands sent to devices

list_custom_apps

Useful for auditing non-store software deployments. Lists all custom applications

list_devices

Returns device names, IDs, and OS versions. Use this as the main tool for auditing the device fleet. Lists all managed Apple devices in Kandji

list_parameters

Useful for auditing available security controls. Lists all library parameters (policies)

list_users

Useful for identifying device owners and primary users. Lists all users associated with devices

Example Prompts for Kandji in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Kandji immediately.

"List all managed Mac computers in Kandji."

"Show me the details for device ID 'abc-123'."

"Check recent administrative activity in Kandji."

Troubleshooting Kandji MCP Server with CrewAI

Common issues when connecting Kandji to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Kandji + CrewAI FAQ

Common questions about integrating Kandji MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.