How to Use the Emissions API MCP in Vercel AI SDK

Q: Can I use Vercel AI SDK to compare different gases using the Emissions API?

Yes, you can run parallel tool calls. Your agent can call getnitrogendioxide and getcarbonmonoxide simultaneously, streaming both datasets into a single Vercel AI SDK UI component for side-by-side comparison.

Q: How do I pull the complete list of trackable gases?

Have your agent call getavailableproducts at the start of the session. This returns the active catalog of gases, allowing the model to decide whether to query getozone or other specific datasets based on user requests.

Stream real-time global pollution data directly into your Next.js frontend with Vercel AI SDK and the Emissions API.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Emissions API MCP to Vercel AI SDK

Create your Vinkius account to connect Emissions API 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 Emissions API with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Live Carbon Monoxide Maps

The Emissions API MCP Server exposes `get_carbon_monoxide` to stream raw carbon monoxide readings directly to your React components. Instead of making users stare at a blank screen while a heavy database query runs, the Vercel AI SDK streams the data chunks as they arrive from the satellite feeds. Your frontend receives the raw coordinates and parts-per-million values instantly. You combine `get_available_products` to let users toggle between different atmospheric gases without triggering full page reloads or blocking the main thread on your Edge Functions.

Render Spatial GeoJSON in Vercel AI SDK UI Components

This integration lets your agent fetch spatial boundaries using `get_geojson_emissions` and pipe the coordinates directly into interactive Mapbox or Leaflet layers. The Vercel AI SDK handles the stream, rendering the vector shapes on the fly as your agent processes the geographic queries. By avoiding intermediate server-side rendering steps, you get raw spatial payloads straight to the client. Your agent can call `get_nitrogen_dioxide` to cross-reference localized traffic corridors with the GeoJSON shapes, updating the UI layer in real-time.

Zero-Latency Ozone Tracking with the Vercel AI SDK

Measuring atmospheric decay requires fast data pipelines, which this MCP Server delivers by exposing `get_ozone` directly to your edge-rendered AI client. The Vercel AI SDK coordinates the tool execution, letting you pipe ozone concentration metrics directly into real-time charts. You don't need to write complex polling mechanisms or manage socket connections manually. By combining `get_methane` with your ozone queries, the agent feeds the combined dataset to your streaming text generation function for instant, live-updating environmental reports.

Setup guide

Set up Emissions API 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 Emissions API 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 Emissions API 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 Emissions API. 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 Emissions API 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 Emissions API MCP in Vercel AI SDK

It connects via a lightweight MCP client that translates tool calls into streaming JSON payloads. Your Vercel AI SDK application receives these chunks over an edge-compatible HTTP transport, allowing your UI to render emission concentrations without waiting for the entire payload to resolve.

Yes, you can run parallel tool calls. Your agent can call `get_nitrogen_dioxide` and `get_carbon_monoxide` simultaneously, streaming both datasets into a single Vercel AI SDK UI component for side-by-side comparison.

No, you do not need a dedicated backend server. The Vercel AI SDK connects directly to the hosted MCP endpoint, executing queries like `get_methane` inside lightweight Edge Functions to keep your bundle size small.

Have your agent call `get_available_products` at the start of the session. This returns the active catalog of gases, allowing the model to decide whether to query `get_ozone` or other specific datasets based on user requests.

All geospatial coordinates, bounding boxes, and raw gas concentration values processed by `get_geojson_emissions` are isolated within a zero-trust V8 sandbox. No raw geographic data is stored or logged on the proxy layer during transit.

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