Compatible with every major AI agent and IDE
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 Vercel AI SDK?
The Vercel AI SDK gives every Fly.io Extended tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 28 tools through Vinkius and stream results progressively to React, Svelte, or Vue components. works on Edge Functions, Cloudflare Workers, and any Node.js runtime.
- —
TypeScript-first: every MCP tool gets full type inference, IDE autocomplete, and compile-time error checking out of the box
- —
Framework-agnostic core works with Next.js, Nuxt, SvelteKit, or any Node.js runtime. same Fly.io Extended integration everywhere
- —
Built-in streaming UI primitives let you display Fly.io Extended tool results progressively in React, Svelte, or Vue components
- —
Edge-compatible: the AI SDK runs on Vercel Edge Functions, Cloudflare Workers, and other edge runtimes for minimal latency
Fly.io Extended in Vercel AI SDK
Fly.io Extended and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Fly.io Extended to Vercel AI SDK 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 Vercel AI SDK
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 Vercel AI SDK 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 Vercel AI SDK
Every tool call from Vercel AI SDK 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 the Vercel AI SDK connect to MCP servers?
Import createMCPClient from @ai-sdk/mcp and pass the server URL. The SDK discovers all tools and provides typed TypeScript interfaces for each one.
Can I use MCP tools in Edge Functions?
Yes. The AI SDK is fully edge-compatible. MCP connections work on Vercel Edge Functions, Cloudflare Workers, and similar runtimes.
Does it support streaming tool results?
Yes. The SDK provides streaming primitives like useChat and streamText that handle tool calls and display results progressively in the UI.
createMCPClient is not a function
Install: npm install @ai-sdk/mcp
Explore More MCP Servers
View all →
JobNimbus
10 toolsManage contacts, jobs, and tasks via JobNimbus CRM API.

IBAN Bank Validator
1 toolsValidate international bank accounts instantly using Modulus 97 checksums. Prevent failed transactions with 100% local precision.

OpenSearch Vector
6 toolsRun k-NN vector searches on OpenSearch — create indexes, upsert embeddings, query similar documents, and manage your vector store from any AI agent.

Chatwoot
8 toolsManage customer engagement via Chatwoot — track conversations, reply to messages, and manage contacts directly from any AI agent.
