How to Use the Albi Restoration MCP in Vercel AI SDK

Q: How do I connect the Albi Restoration MCP Server to Vercel AI SDK?

Run npm install ai @ai-sdk/mcp in your project folder. Initialize the client using createMCPClient with your endpoint URL. Call mcpClient.tools() and pass the array into your streamText function.

Q: What happens if the API goes down during a stream?

Your application can run checkapihealth before initiating heavy data pulls. If the endpoint drops mid-stream, the SDK catches the error and stops the generation. You handle the fallback UI on your end, plain and simple.

Q: How does Albi Restoration map project roles in Vercel AI SDK?

You call listdefinedprojectroles to pull the available permission tiers. The agent uses this list to validate user requests before attempting changes. This prevents unauthorized commands from hitting the server.

Build live restoration dashboards where Albi project data streams directly into your React frontend using the Vercel AI SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Albi Restoration MCP to Vercel AI SDK

Create your Vinkius account to connect Albi Restoration to Vercel AI SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Albi Restoration with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Albi Restoration MCP Server Data

`list_restoration_projects` fetches your active jobs while the AI client immediately starts rendering the results on screen. Your users don't stare at loading spinners while waiting for the entire payload to arrive. Vercel AI SDK chunks the response from the Albi API directly into your Next.js frontend. You can chain this with `get_project_financial_kpis` to build interactive profit margin tables. The moment a contractor asks for job costs, the numbers appear row by row. It feels instant because the data flows as fast as the endpoint returns it.

Create Records Without Forms

`create_new_restoration_project` requires just a name and primary contact to kick off a new job. Instead of building complex multi-step forms, your users type a natural language prompt. The agent parses the intent and hits the endpoint. If the user forgets a detail, the SDK prompts them for the missing information before executing. You hook up `create_new_contact` the same way. Field workers submit new leads from their phones using just their voice.

Track Equipment Live

`list_inventory_equipment` exposes asset locations and status straight to your UI. When an adjuster asks where the dehumidifiers are, the agent pulls the exact inventory count. This eliminates frantic text threads between the office and the field. Combine this with `list_project_activities` to map out exactly which crew is using what gear. Your interface updates in real-time as the agent correlates tasks with hardware. The whole system runs over a single HTTP transport connection.

Setup guide

Set up Albi Restoration MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Albi Restoration tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Albi Restoration transactions",
});

console.log(text);
await mcpClient.close();

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Albi. 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.

Connect Albi Restoration now

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 Albi Restoration MCP in Vercel AI SDK

Run `npm install ai @ai-sdk/mcp` in your project folder. Initialize the client using `createMCPClient` with your endpoint URL. Call `mcpClient.tools()` and pass the array into your `streamText` function.

Yes, the Vinkius platform handles the underlying API keys. You pass your single endpoint token through the `authProvider` configuration. The MCP client manages the secure transport automatically.

Your application can run `check_api_health` before initiating heavy data pulls. If the endpoint drops mid-stream, the SDK catches the error and stops the generation. You handle the fallback UI on your end, plain and simple.

You call `list_defined_project_roles` to pull the available permission tiers. The agent uses this list to validate user requests before attempting changes. This prevents unauthorized commands from hitting the server.

Vinkius runs the connection inside a V8 Isolate Sandbox that destroys itself after the request finishes. Your project financial KPIs and contact details never touch disk storage. Zero-trust architecture means nothing persists between queries.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript