How to Use the Fulcrum MCP in Vercel AI SDK

Q: How do I connect the Fulcrum MCP Server to my Vercel AI SDK project?

First, npm install ai @ai-sdk/mcp. Then use createMCPClient and pass your Vinkius server URL in the http transport option. You can then get the tools by calling mcpClient.tools().

Q: Can my Vercel AI SDK app filter Fulcrum records?

Yes. Your agent can use the listfieldrecords tool with a formid to get specific records, or it can run a full queryrecordssql statement for more complex filtering. The results will stream back to your UI.

Q: How can I use the Vercel AI SDK to build a UI for creating Fulcrum records?

Have your agent call getformschema first. Use the schema it returns to dynamically generate form fields in your React or Next.js app. When the user submits, pass their input to the createrecord tool.

Connect your Vercel AI SDK app to Fulcrum and watch field data appear in your UI in real-time. No spinners, just live data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Fulcrum MCP to Vercel AI SDK

Create your Vinkius account to connect Fulcrum 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 Fulcrum with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Field Data, Stream Results

Tell your agent to find Fulcrum records. It can run a simple search with `list_field_records` or execute a complex join using `query_records_sql`. The Vercel AI SDK then streams the data directly from the tool call into your frontend. Your users won't see a loading spinner. They'll see tables and lists populating live in your Next.js or Svelte app. You can even use `get_form_schema` first to build a dynamic UI that perfectly matches the data before it even arrives.

Build Interactive Forms with your MCP Server

Your agent doesn't just read data—it writes it. A user can ask your AI to log a new field inspection, and the agent will use the `create_record` tool to add it to Fulcrum instantly. The whole exchange happens right in your app's chat interface. This turns your frontend into a proper internal tool. Staff can manage Fulcrum data using natural language, and because the Vercel AI SDK streams the interaction, it feels immediate. You're not just building a data viewer; you're building a command center.

Manage Teams and Webhooks Live

This isn't just about form records. Your agent can check on the system itself. Have it call `list_organization_members` or `list_member_roles` to pull team info directly into an admin dashboard you've built. Or, ask your agent to audit your automation by calling `list_webhooks`. Since the Vercel AI SDK streams every response, you can build a live monitoring view that shows your webhook configurations the moment they're fetched from the MCP server.

Setup guide

Set up Fulcrum 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 Fulcrum 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 Fulcrum 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 Fulcrum. 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 Fulcrum 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 Fulcrum MCP in Vercel AI SDK

First, `npm install ai @ai-sdk/mcp`. Then use `createMCPClient` and pass your Vinkius server URL in the http transport option. You can then get the tools by calling `mcpClient.tools()`.

Yes. Your agent can use the `list_field_records` tool with a `form_id` to get specific records, or it can run a full `query_records_sql` statement for more complex filtering. The results will stream back to your UI.

Have your agent call `get_form_schema` first. Use the schema it returns to dynamically generate form fields in your React or Next.js app. When the user submits, pass their input to the `create_record` tool.

Vinkius manages the server-side auth using the Fulcrum token you provide. For your app's frontend, the `createMCPClient` function supports an `authProvider` so you can handle your own user-facing authentication.

Your agent only accesses the Fulcrum data it's told to. This server operates on your form records, user lists, and form schemas. Every connection runs through Vinkius's zero-trust platform, using single-use sandboxes for each tool call.

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