How to Use the Emissions API MCP in OpenAI Agents SDK

Q: How do I initialize the Emissions API within the OpenAI Agents SDK using an MCP Server?

Install the package using pip, then instantiate MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server instance directly into the mcpservers list of your Agent constructor to let the OpenAI Agents SDK discover the gas tracking tools.

Q: Can the OpenAI Agents SDK handle parallel calls to the Emissions API?

Yes, the OpenAI Agents SDK manages parallel execution of getozone and getnitrogendioxide to compare regional atmospheric levels. Your agent can run these queries simultaneously to analyze multiple gases without blocking your main loop.

Q: How do agent handoffs work when tracking gas levels using the Emissions API with the OpenAI Agents SDK?

A general triaging agent identifies a gas anomaly using getmethane, then hands off the context to an OpenAI Agents SDK mapping agent. The MCP integration handles the transport layer cleanly while the OpenAI dashboard logs the handoff.

Q: What is the fastest way to improve query performance for gas tools in the OpenAI Agents SDK?

Set the cacheToolsList parameter to true in your OpenAI Agents SDK connection configuration. This stops the agent from refetching the gas endpoints before every lookup, cutting down latency on live queries.

Deploy production environmental agents that pull real-time gas data using the OpenAI Agents SDK with built-in guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Emissions API to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discover emissions tools in OpenAI Agents SDK

The `get_available_products` tool registers directly with your OpenAI Agents SDK runtime to expose all active gas products instantly. Your agents query this index to map available gases before running deeper environmental audits. You do not write manual schemas or configuration files for gas queries in the OpenAI Agents SDK. The SDK handles the handshake and mounts the entire suite of tools directly to your agent system so it can start calling endpoints immediately.

Safeguard carbon monoxide and methane queries

The `get_carbon_monoxide` and `get_methane` tools validate input parameters through OpenAI Agents SDK guardrails before execution. This prevents your production system from making broken or out-of-bounds API requests during heavy automated monitoring runs. When an OpenAI Agents SDK agent detects a localized gas spike, it hands off the task to a specialized analysis agent with full execution traces. The tracing dashboard records every step of the gas discovery process, giving you an audit trail for regulatory compliance.

Map geographic gas spikes with zero-config MCP Server

The `get_geojson_emissions` tool outputs structured geographic data that your OpenAI Agents SDK agent parses into spatial coordinates. The agent automatically processes these coordinates to pinpoint exact pollution zones. By connecting this MCP Server to your OpenAI Agents SDK multi-agent pipeline, you can run automated daily sweeps for gas anomalies. One agent pulls the raw geojson, while another formats it for your internal environmental database.

Setup guide

Set up Emissions API MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Emissions API tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Emissions API tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Emissions API tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Emissions API Agent",
            instructions="You have access to Emissions API tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install the package using pip, then instantiate `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server instance directly into the `mcp_servers` list of your Agent constructor to let the OpenAI Agents SDK discover the gas tracking tools.

Yes, the OpenAI Agents SDK manages parallel execution of `get_ozone` and `get_nitrogen_dioxide` to compare regional atmospheric levels. Your agent can run these queries simultaneously to analyze multiple gases without blocking your main loop.

A general triaging agent identifies a gas anomaly using `get_methane`, then hands off the context to an OpenAI Agents SDK mapping agent. The MCP integration handles the transport layer cleanly while the OpenAI dashboard logs the handoff.

Set the `cacheToolsList` parameter to true in your OpenAI Agents SDK connection configuration. This stops the agent from refetching the gas endpoints before every lookup, cutting down latency on live queries.

The server processes your gas query parameters—like coordinate bounds for ozone or nitrogen dioxide—inside an ephemeral V8 sandbox before returning them to the OpenAI Agents SDK. No search history or geographic coordinates are stored on disk, and the connection closes immediately after the data payload is delivered.

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