How to Use the DoiT MCP in CrewAI

Q: How do CrewAI agents collaborate on DoiT cost alerts?

One CrewAI agent monitors DoiT's listcostanomalies while another uses getassetdetails to investigate the flagged resources. CrewAI coordinates this DoiT data handoff using shared context and sequential task execution.

Q: How does DoiT handle multi-cloud environments in CrewAI?

The listcloudassets tool returns unified DoiT data for AWS, GCP, and Azure directly to CrewAI. Your CrewAI agents parse this single DoiT payload to analyze costs across all cloud providers without needing separate integrations.

Deploy a collaborative crew of specialized agents in CrewAI to audit cloud spend and manage DoiT cost alerts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DoiT MCP to CrewAI

Create your Vinkius account to connect DoiT 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 DoiT with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Multi-Agent DoiT FinOps Teams via CrewAI

The `get_billing_cost_summary` tool provides your primary CrewAI auditor agent with an instant snapshot of global cloud spend tracked by DoiT. In a CrewAI setup, this auditor agent passes the high-level DoiT numbers to an analyst agent to identify underlying trends. By sharing memory across the CrewAI team, your agents collaborate to trace DoiT cost spikes back to specific cloud accounts. The CrewAI analyst agent requests deeper logs from other DoiT tools, building a complete picture of your financial posture.

Investigate DoiT Cost Spikes with CrewAI Agents

The `list_critical_cost_spikes` tool triggers your monitoring agent in CrewAI whenever a massive spend deviation is detected by DoiT. This CrewAI agent immediately hands the DoiT spike details to an investigator agent to diagnose the root cause. The investigator agent in CrewAI calls DoiT's `search_cloud_assets` to locate the offending resource across AWS, GCP, or Azure. It compiles a diagnostic CrewAI report detailing the DoiT asset's configuration, saving hours of manual digging.

Map DoiT Accounts Using Collaborative CrewAI Agents

The `list_connected_cloud_accounts` tool allows your mapping agent in CrewAI to catalog every active cloud environment managed by DoiT. CrewAI distributes this DoiT account list across specialized agents, each responsible for auditing a different provider. The CrewAI agents run parallel checks using DoiT's `get_asset_details` to verify compliance with company tagging policies. Any untagged or rogue DoiT resource is flagged and compiled into a master CrewAI inventory report.

Setup guide

Set up DoiT 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 DoiT tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

One CrewAI agent monitors DoiT's `list_cost_anomalies` while another uses `get_asset_details` to investigate the flagged resources. CrewAI coordinates this DoiT data handoff using shared context and sequential task execution.

Yes, you can use a tool filter when registering the MCP Server to restrict DoiT tools in CrewAI. This restricts your CrewAI researcher agent to `search_cloud_assets` while reserving DoiT billing tools for your analyst agent.

The `list_cloud_assets` tool returns unified DoiT data for AWS, GCP, and Azure directly to CrewAI. Your CrewAI agents parse this single DoiT payload to analyze costs across all cloud providers without needing separate integrations.

You pass your Vinkius MCP Server endpoint URL directly into the CrewAI agent's `mcps` array to access DoiT. CrewAI automatically discovers the 10 available DoiT tools and exposes them to your agent team.

Only DoiT metadata like resource tags, budget thresholds, and cost summaries are accessed by CrewAI. The Vinkius MCP Server executes all queries in an ephemeral sandbox, preventing persistent caching of your DoiT cloud financial records by CrewAI.

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