Bring Fly Io
to CrewAI
Learn how to connect Fly.io Extended to CrewAI and start using 28 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
GDPR Free for SubscribersCompatible with every major AI agent and IDE
Gemini
What is the Fly.io Extended MCP Server?
Connect your Fly.io account to any AI agent to orchestrate your cloud infrastructure through natural language. This server provides full access to the Fly Machines API, allowing for granular control over global deployments.
What you can do
- App Management — Create, list, and delete Fly Apps across your organizations.
- Machine Lifecycle — Start, stop, suspend, and update individual Machines with precise configuration control.
- Storage & Volumes — Provision, extend, and manage persistent volumes and snapshots for your stateful applications.
- Network & Security — Manage ACME and custom certificates, and request OIDC tokens for secure workload identity.
- Real-time Monitoring — Wait for specific machine states and fetch detailed metadata for debugging and orchestration.
How it works
- Subscribe to this server
- Enter your Fly.io Personal Access Token
- Start deploying and managing your global infrastructure from Claude, Cursor, or any MCP client
Who is this for?
- DevOps Engineers — Automate scaling, machine restarts, and volume management without leaving the terminal or chat interface.
- Full-stack Developers — Deploy new app instances and check machine statuses directly from your code editor.
- SRE Teams — Quickly inspect infrastructure health and manage certificates during incident response.
Built-in capabilities (28)
Trigger DNS validation check for a certificate
Request a Let's Encrypt certificate
Create a new Fly App
Import a custom PEM certificate
Create a lease for a Machine
Requires a config object containing at least the image. Create a new Fly Machine
Create a new volume
Delete a Fly App
Remove hostname and certificates
Delete a Machine
Delete a volume
Increase volume size
Get details about a Fly App
Get certificate details
Get Machine details
Get volume details
List Fly Apps
List all certificates for an app
List all Machines in an app
List volume snapshots
List all volumes in an app
Release a lease for a Machine
Request an OpenID Connect (OIDC) token
Start a Machine
Stop a Machine
Suspend a Machine
Update Machine configuration
Wait for a specific Machine state
Why CrewAI?
When paired with CrewAI, Fly.io Extended becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Fly.io Extended tools autonomously, one agent queries data, another analyzes results, a third compiles reports, all orchestrated through Vinkius with zero configuration overhead.
- —
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 Vinkius Edge URL directly in the
mcpsparameter 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
Fly.io Extended in CrewAI
Fly.io Extended and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Fly.io Extended to CrewAI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Fly.io Extended in CrewAI
The Fly.io Extended 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. All 28 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in CrewAI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* 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
How Vinkius secures
Fly.io Extended for CrewAI
Every tool call from CrewAI to the Fly.io Extended MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I start or stop a specific Fly Machine using this server?
Yes. You can use the start_machine and stop_machine tools by providing the app name and the specific Machine ID. You can also use suspend_machine for compatible workloads.
How do I create a new application in a specific organization?
Use the create_app tool. You will need to provide a unique app_name and the org_slug of the target organization where you want the app to be provisioned.
Is it possible to manage persistent storage volumes?
Absolutely. The server includes tools like create_volume, list_volumes, extend_volume, and delete_volume to handle the full lifecycle of your Fly Volumes.
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.
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
Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.
Explore More MCP Servers
View all →
AbstractAPI
10 toolsEquip your AI agent with AbstractAPI's data enrichment — validate emails, geolocate IPs, check phone numbers, and enrich company data.
FOSSA (License Compliance)
6 toolsManage license compliance and security vulnerabilities via FOSSA — list projects, inspect revisions, and track dependencies directly from your AI agent.
Manage your LinkedIn presence — audit organizations, posts, and profile via AI.
GitHub
12 toolsManage repositories, track issues, and search code via AI agents with GitHub.