Bring Voice Ai
to Vercel AI SDK
Learn how to connect Retell AI to Vercel AI SDK and start using 11 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Retell AI MCP Server?
Connect your Retell AI account to any AI agent and take full control of your conversational voice orchestration through natural conversation. Retell AI provides a premier platform for building human-like voice agents, and this integration allows you to create agents, initiate phone or web calls, and monitor LLM configurations directly from your chat interface.
What you can do
- Agent & Persona Orchestration — List all managed voice agents and retrieve detailed persona metadata, including creating new agents programmatically.
- Call Lifecycle Management — Initiate and monitor real-time phone or web calls and retrieve detailed call metadata including recordings and transcripts directly from the AI interface.
- LLM & Brain Control — Access and monitor your Retell LLM configurations to ensure your agents always have the correct logic and knowledge via natural language.
- Phone Number Intelligence — List available phone numbers to maintain a clear overview of your telephony infrastructure.
- Operational Monitoring — Track system responses and manage agent settings using simple AI commands to ensure your voice operations are always optimized.
How it works
1. Subscribe to this server
2. Enter your Retell AI API Key from your dashboard settings
3. Start managing your voice agents from Claude, Cursor, or any MCP-compatible client
No more manual call logs or complex agent configuration. Your AI acts as a dedicated voice operations manager or AI lead.
Who is this for?
- AI Developers & Product Managers — quickly retrieve call details and monitor agent performance without switching apps.
- Customer Support Operations — automate the management of voice personas and track call history via natural conversation.
- Operations Teams — streamline the retrieval of agent metadata and monitor organizational voice health directly within the chat.
Built-in capabilities (11)
Create a new AI voice agent
Get details for a voice agent
Get details and transcript for a call
Get metadata for a response engine
Get details for a specific phone number
List call logs and history
List internal response engines
List registered phone numbers
List all AI voice agents
Initiate an outbound phone call
Initialize a browser-based call
Why Vercel AI SDK?
The Vercel AI SDK gives every Retell AI tool full TypeScript type inference, IDE autocomplete, and compile-time error checking. Connect 11 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 Retell AI integration everywhere
- —
Built-in streaming UI primitives let you display Retell AI 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
Retell AI in Vercel AI SDK
Retell AI and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Retell AI 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 | 3,400+ 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 Retell AI in Vercel AI SDK
The Retell AI 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 11 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
Retell AI for Vercel AI SDK
Every tool call from Vercel AI SDK to the Retell AI MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can my AI automatically create a new phone call to a customer using a specific agent?
Yes! Use the create_phone_call tool. Provide the destination phone number and the agent_id, and your agent will trigger the outbound AI voice call instantly.
How do I list all my available Retell voice agents?
Simply ask the agent to run the list_agents action. It will retrieve the full catalog of voice agents configured in your Retell AI account.
How do I find my Retell AI API Key?
Log in to your Retell AI dashboard, navigate to Settings > API Keys, and you will find your unique secret API key there.
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
