How to Use the AirVisual MCP in Claude Code

Q: How do I configure the AirVisual MCP Server transport settings in Claude Code?

Use the command-line tool helper: claude mcp add --transport http airvisual -- . This registers the server in your local config file, allowing the CLI to access the tools instantly.

Q: What is the fastest way to get local air metrics?

The fastest tool is getnearestcitybyip. It bypasses the need to manually supply latitude and longitude, pulling immediate localized weather and pollution metrics based on your current terminal session's network point.

Pipe live AirVisual weather and AQI metrics directly into your terminal scripts using Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AirVisual MCP to Claude Code

Create your Vinkius account to connect AirVisual to Claude Code 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 AirVisual with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe Real-Time AQI Data Directly to Your Shell

Claude Code lets you query environmental metrics without leaving your terminal. Run a single command to call `get_nearest_city_by_ip` and pipe the resulting weather and pollution payload directly into grep, jq, or local config scripts. This makes it incredibly easy to parse raw air quality indexes on the fly using the MCP toolset. You can write quick bash aliases that dump current weather stats directly into your terminal greeting or system logs.

Automate Environmental Testing via Claude Code

Integrate this MCP Server into your automated deployment pipelines. Claude Code can run headless scripts that verify global API responses using `get_city_data` to ensure your weather monitoring services are parsing external payloads correctly before staging a release. Because the server runs in a secure, managed sandbox, your runners don't need complex local SDK installations. Claude Code executes the checks, validates the output, and flags any API schema discrepancies instantly.

Batch Query Global Stations via the Command Line

Claude Code can loop through global locations to audit monitoring networks. By executing `list_countries`, `list_states`, and `list_cities`, you can output clean text lists of supported stations directly to stdout. Combine these lists with `get_station_data` to quickly verify which sensors are reporting live metrics. It is a highly efficient way to run network-wide diagnostics without ever opening a web browser.

Setup guide

Set up AirVisual MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see airvisual-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest AirVisual transactions." It will automatically discover and invoke the available AirVisual tools.

Terminal

claude mcp add --transport http airvisual-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the AirVisual MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "airvisual-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 AirVisual. 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 AirVisual 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 AirVisual MCP in Claude Code

You execute the query directly in your terminal. Ask Claude Code to check local AQI, and it will run the MCP command to print the raw weather metrics straight to your standard output.

Yes. You can tell Claude Code to write a shell script that queries `get_city_data` and redirects the JSON output into a local log file, which you can then schedule with a system cron job.

Use the command-line tool helper: `claude mcp add --transport http airvisual -- `. This registers the server in your local config file, allowing the CLI to access the tools instantly.

The fastest tool is `get_nearest_city_by_ip`. It bypasses the need to manually supply latitude and longitude, pulling immediate localized weather and pollution metrics based on your current terminal session's network point.

Your IP addresses are only used by the server to resolve your nearest monitoring station. Vinkius executes this request within an isolated sandbox, ensuring your network details and local weather data are never exposed or stored.

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