How to Use the Emissions API MCP in LlamaIndex

Q: How do I set up the Emissions API with LlamaIndex?

Install llama-index-tools-mcp and instantiate a BasicMCPClient with the server URL. Wrap it in an McpToolSpec and pass the async tool list to your agent.

Q: Can LlamaIndex embed the output from the Emissions API?

It handles this natively. You execute getozone via the MCP Server, and LlamaIndex converts the resulting JSON into text nodes for immediate vectorization and storage.

Q: How does the agent know when to query the Emissions API in LlamaIndex?

The FunctionAgent reads the tool descriptions for getcarbonmonoxide and others. If the user prompt asks about recent air quality, the agent maps the intent directly to the specific gas endpoint.

Q: Can I filter which tools the LlamaIndex agent accesses?

You pass an allowedtools array during setup. If you only want the agent mapping spatial data, restrict it to getgeojsonemissions and block the individual gas queries.

Q: Is my location data secure when using LlamaIndex with this server?

Your geographic bounding boxes sent to getmethane hit a zero-trust endpoint. The Vinkius infrastructure processes the coordinates to fetch the emissions data and destroys the container state immediately after.

Index live atmospheric telemetry and build RAG applications over the Emissions API using LlamaIndex.

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 LlamaIndex

Create your Vinkius account to connect Emissions API to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Emissions API Output for RAG

The `get_nitrogen_dioxide` tool acts as a direct data source for your LlamaIndex vector store. You query the API for daily traffic pollution metrics, and the framework embeds the raw numbers alongside your internal city planning documents. When a user asks about historical air quality, the agent doesn't guess. It runs a semantic search against the indexed MCP tool outputs, pulling exact parts-per-million readings to ground its response in actual environmental telemetry.

Map GeoJSON into Searchable Nodes

Your LlamaIndex application calls `get_geojson_emissions` to ingest spatial boundaries and pollution densities. The framework chunks these complex JSON structures into individual document nodes, making geographic regions fully searchable. If you are tracking a factory's impact, the agent queries the index for specific coordinates and cross-references them with `get_carbon_monoxide` data. The MCP Server feeds the exact spatial context required for accurate semantic retrieval.

Ground Your LlamaIndex Function Agent

You pass `get_available_products` to your `FunctionAgent` so it knows exactly which gas databases it can query. The agent reads the available products list and decides whether to pull methane or ozone data based on the user's prompt. For agricultural research, the agent triggers `get_methane` and immediately synthesizes the returned metrics with your local research papers. This MCP integration ensures your RAG pipeline always has access to live atmospheric conditions.

Setup guide

Set up Emissions API MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Emissions API MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Emissions API tools.",
)
response = await agent.run("List recent Emissions API data")

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 LlamaIndex

Install `llama-index-tools-mcp` and instantiate a `BasicMCPClient` with the server URL. Wrap it in an `McpToolSpec` and pass the async tool list to your agent.

It handles this natively. You execute `get_ozone` via the MCP Server, and LlamaIndex converts the resulting JSON into text nodes for immediate vectorization and storage.

The `FunctionAgent` reads the tool descriptions for `get_carbon_monoxide` and others. If the user prompt asks about recent air quality, the agent maps the intent directly to the specific gas endpoint.

You pass an `allowed_tools` array during setup. If you only want the agent mapping spatial data, restrict it to `get_geojson_emissions` and block the individual gas queries.

Your geographic bounding boxes sent to `get_methane` hit a zero-trust endpoint. The Vinkius infrastructure processes the coordinates to fetch the emissions data and destroys the container state immediately after.

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