How to Use the Fly.io Extended MCP in CrewAI
Deploy a team of autonomous SRE agents to manage your Fly.io Extended infrastructure using CrewAI.
Works with every AI agent you already use
…and any MCP-compatible client
Connect Fly.io Extended MCP to CrewAI
Create your Vinkius account to connect Fly.io Extended 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.
Provision Apps and Compute in Teams
`create_app` registers new application namespaces on the Fly.io platform. Within a CrewAI team, a developer agent can request a new environment, prompting the SRE agent to execute this tool. Once the app exists, `create_machine` deploys the actual microVMs running your containerized code. The crew coordinates these steps, passing the newly generated app name from one agent to the next.
Manage Volumes via CrewAI Multi-Agent Crews
`list_volumes` scans your active Fly.io applications to audit disk usage across all regions. This MCP Server allows your crew to identify orphaned or over-provisioned storage. If an active volume is running out of space, `extend_volume` increases its size automatically. The SRE agent executes the expansion while a coordinator agent logs the change to your team's tracking system.
Recover Unhealthy Machines Autonomously
`list_machines` fetches the operational status of all microVMs running in a specific Fly.io app. Your CrewAI monitoring agent parses this data to detect crashed or unresponsive instances. When a failure is detected, `update_machine` or `start_machine` is called by the recovery agent to reboot the VM. This multi-agent collaboration resolves infrastructure outages without requiring human SRE intervention.
Set up Fly.io Extended MCP in CrewAI
Prerequisites
- Python 3.10+ installed
-
crewaipackage (pip install crewai) - Active Vinkius subscription with a valid endpoint token
- 1
Install CrewAI
Run
pip install crewaito install the framework. MCP support is built-in via themcpsparameter. - 2
Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the
mcpslist. 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
Crewwith your agent and tasks. Callcrew.kickoff()— the agent will automatically invoke Fly.io Extended tools as needed.
from crewai import Agent, Task, Crew
agent = Agent(
role="Fly.io Extended Analyst",
goal="Access and analyze Fly.io Extended data via MCP.",
backstory="Expert analyst with direct Fly.io Extended access.",
mcps=[
"https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
],
)
task = Task(
description="List recent Fly.io Extended transactions",
agent=agent,
expected_output="A summary of recent activity",
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result) Prerequisites
- Python 3.10+ installed
-
crewai+crewai-toolspackages - Active Vinkius subscription with a valid endpoint token
- 1
Install dependencies
Run
pip install crewai crewai-tools. TheMCPServerAdapterhandles lifecycle management and tool conversion. - 2
Connect with MCPServerAdapter
Use
MCPServerAdapteras a context manager withSseServerParameterspointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle. - 3
Assign tools and run
Pass the returned
mcp_toolsto your agent'stoolsparameter. The adapter converts MCP tools to nativeBaseToolobjects compatible with all CrewAI agents.
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="Fly.io Extended Analyst",
goal="Access and analyze Fly.io Extended data via MCP.",
backstory="Expert analyst with direct Fly.io Extended access.",
tools=mcp_tools,
)
task = Task(
description="List recent Fly.io Extended transactions",
agent=agent,
expected_output="A summary of recent activity",
)
crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result) Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Fly.io. 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.
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 Fly.io Extended MCP in CrewAI
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
Start using the Fly.io Extended MCP today
We host it, we monitor it, we maintain it. You just paste one token.