Bring Web Server
to Vercel AI SDK
Learn how to connect Caddy Server to Vercel AI SDK and start using 13 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 Caddy Server MCP Server?
Connect your Caddy Server instance to any AI agent and automate your web infrastructure management through natural conversation.
What you can do
- Configuration Management — Load, get, append, or replace server configurations using JSON or Caddyfile formats.
- Caddyfile Adaptation — Instantly convert Caddyfile text into native Caddy JSON without applying the changes.
- Upstream Monitoring — Check the real-time status and health of your proxy upstreams and backends.
- PKI & Certificates — Inspect internal CA information and retrieve certificate chains for your managed domains.
- Metrics & Observability — Access Prometheus-style metrics to monitor server performance and request traffic.
- Granular Control — Delete specific configuration paths or gracefully stop the server process.
How it works
- Subscribe to this server
- Enter your Caddy Admin API URL (e.g., http://localhost:2019)
- Start managing your reverse proxies and web servers from Claude, Cursor, or any MCP client
Who is this for?
- DevOps Engineers — automate infrastructure updates and monitor backend health without leaving the terminal or chat.
- Web Developers — quickly test and adapt Caddyfile configurations during local development.
- SREs — retrieve live metrics and PKI status to ensure site reliability and security compliance.
Built-in capabilities (13)
Adapts a configuration (e.g., Caddyfile) to JSON without running it
and target is array, expands payload array and appends elements. Sets or replaces an object; appends to an array in Caddy config
Deletes the value at the named path in Caddy config
Leave empty for full config. Exports the configuration at the specified path as JSON
Access a configuration object directly via its @id field
Exposes metrics in Prometheus exposition format
Returns information about a particular PKI app CA
Returns the certificate chain for a particular CA
Returns the current status of configured proxy upstreams
Creates a new object or inserts into an array at a specific index
Use application/json for native JSON, or text/caddyfile for Caddyfile. Sets or replaces the active Caddy configuration
Strictly replaces an existing object or array element in Caddy config
Gracefully shuts down the Caddy server and exits the process
Why Vercel AI SDK?
The Vercel AI SDK gives every Caddy Server tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 13 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 Caddy Server integration everywhere
- —
Built-in streaming UI primitives let you display Caddy Server 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
Caddy Server in Vercel AI SDK
Caddy Server and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Caddy Server 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 Caddy Server in Vercel AI SDK
The Caddy Server 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 13 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
Caddy Server for Vercel AI SDK
Every tool call from Vercel AI SDK to the Caddy Server MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I use a Caddyfile instead of JSON to update my configuration?
Yes! Use the load_config tool and set the content_type to text/caddyfile. You can also use adapt_config to preview the JSON conversion before applying it.
How can I monitor the health of my load-balanced backends?
Use the get_upstreams tool. It returns the current status and health metrics of all configured proxy upstreams in your Caddy instance.
Is it possible to remove a specific site or route without resetting the whole server?
Absolutely. Use delete_config with the specific path (e.g., apps/http/servers/srv0/routes/1) to remove only that element from the active configuration.
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 →
vCita
12 toolsRun your small business with online scheduling, payment collection, and client management that keeps everything in one place.
Knackly
8 toolsGenerate legal and business documents from smart templates with conditional logic that adapts content to every unique situation.
Shutterstock
9 toolsEquip your AI agent to radically sift through Shutterstock's immense media vault. Search high-quality images, videos, audio, and audit editorial licenses directly from your prompt.
Dub.co
10 toolsManage your short links via Dub.co — create, track, and analyze your link performance directly from any AI agent.