How to Use the Hasura (Instant GraphQL & REST Engine) MCP in Vercel AI SDK

Q: How do I connect the Hasura (Instant GraphQL & REST Engine) to Vercel AI SDK?

Install @ai-sdk/mcp. Initialize the connection using createMCPClient with an HTTP transport URL pointing to your endpoint.

Q: Can Vercel AI SDK run Hasura (Instant GraphQL & REST Engine) metadata operations?

Yes. The executemetadata tool allows your agent to modify relationships, permissions, and event triggers. You just pass the JSON payload through the client.

Q: How do I check database health using Hasura (Instant GraphQL & REST Engine) with Vercel AI SDK?

Pass the checkhealth tool to your generateText call. You can enable strict mode to verify metadata consistency alongside basic server uptime.

Q: What happens if a GraphQL mutation fails during a stream?

The executegraphql tool returns the standard GraphQL error object. Your frontend catches this payload and displays the exact failure reason to the user.

Q: How does the MCP server handle data privacy for pgdump operations?

The pgdump tool directly accesses your raw Postgres schema and table rows. Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox, meaning your raw SQL dumps vanish from memory the millisecond the transfer completes.

Stream live GraphQL query results directly to your Next.js frontend using the Hasura (Instant GraphQL & REST Engine) MCP Server for 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 Hasura (Instant GraphQL & REST Engine) MCP to Vercel AI SDK

Create your Vinkius account to connect Hasura (Instant GraphQL & REST Engine) 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 Hasura (Instant GraphQL & REST Engine) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Vercel AI SDK Queries Live

The `execute_graphql` tool lets your Vercel AI SDK client run queries, mutations, and batched requests directly against your Hasura engine. You pass the query, and the agent streams the JSON response straight back into your React or Next.js UI components. No loading spinners required. Because the MCP Server handles the transport layer, your edge functions stay incredibly thin. You just call the tool, and the raw data appears on the screen exactly as the database returns it.

Expose Query Execution Plans

The `explain_graphql` tool translates complex GraphQL requests into their underlying SQL execution plans. Your agent can read this output to identify slow queries before they hit production. It reads the raw database logic right inside the chat window. Developers building internal dashboards can use this to show users exactly how their custom queries perform. The agent fetches the plan, formats the SQL, and displays the performance metrics instantly.

Trigger Direct Postgres Dumps

The `pg_dump` tool executes a full schema and data dump on any connected Postgres source through the Hasura instance. Your client triggers the command, pulling down the raw SQL output for immediate backup or migration tasks. You don't need to leave the frontend interface to handle database maintenance. The agent runs the dump, confirms completion, and can even stream the progress logs if configured correctly.

Setup guide

Set up Hasura (Instant GraphQL & REST Engine) 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 Hasura (Instant GraphQL & REST Engine) 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 Hasura (Instant GraphQL & REST Engine) 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 Hasura. 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 Hasura (Instant GraphQL & REST Engine) 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 Hasura (Instant GraphQL & REST Engine) MCP in Vercel AI SDK

Install `@ai-sdk/mcp`. Initialize the connection using `createMCPClient` with an HTTP transport URL pointing to your endpoint.

Yes. The `execute_metadata` tool allows your agent to modify relationships, permissions, and event triggers. You just pass the JSON payload through the client.

Pass the `check_health` tool to your `generateText` call. You can enable strict mode to verify metadata consistency alongside basic server uptime.

The `execute_graphql` tool returns the standard GraphQL error object. Your frontend catches this payload and displays the exact failure reason to the user.

The `pg_dump` tool directly accesses your raw Postgres schema and table rows. Vinkius runs this MCP Server in an ephemeral V8 Isolate Sandbox, meaning your raw SQL dumps vanish from memory the millisecond the transfer completes.

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