How to Use the AQICN MCP in CrewAI

Q: Can I restrict which AQICN MCP Server tools my CrewAI agents access?

Import MCPServerHTTP from crewai.mcp and use the toolfilter parameter. You give your researcher agent access to getcityfeed while preventing it from touching getipfeed.

Deploy autonomous CrewAI agents that monitor global air quality, analyze pollution trends, and execute health alerts using the AQICN MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AQICN MCP to CrewAI

Create your Vinkius account to connect AQICN to CrewAI 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 AQICN with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CrewAI Teams Analyze AQICN Data

`get_city_feed` provides raw atmospheric data to your researcher agents. You assign one agent to continuously monitor the air quality index for major metropolitan areas, watching for dangerous spikes in carbon monoxide or particulate matter. That researcher shares its findings in the crew's memory. A separate analyst agent reads the PM2.5 numbers and drafts an executive summary, while a third communication agent pushes the final warning to your Slack channel.

Coordinate Regional Sensor Scans

`get_map_bounds` lets your geographical mapping agent identify every active sensor within a defined territory. The agent grabs the station list and delegates the individual data collection to sub-agents. Those workers then hit `get_station_feed` using the specific UIDs. They pull the temperature, wind speed, and pollutant concentration for each block, compiling a massive regional dataset without you writing any loop logic.

Autonomous Station Discovery

`search_stations` gives your crew the ability to find monitoring hardware on the fly via this MCP server. If you instruct the system to investigate pollution in a specific province, the agents query the text search to locate the right hardware before pulling the metrics. The `get_ip_feed` tool serves as a quick localized check. An agent reads incoming user tickets, extracts the IP address, and instantly knows the environmental conditions of the person submitting the request.

Setup guide

Set up AQICN MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke AQICN tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="AQICN Analyst",
    goal="Access and analyze AQICN data via MCP.",
    backstory="Expert analyst with direct AQICN access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent AQICN transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="AQICN Analyst",
        goal="Access and analyze AQICN data via MCP.",
        backstory="Expert analyst with direct AQICN access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent AQICN transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 AQICN. 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 AQICN 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 AQICN MCP in CrewAI

Add your Vinkius endpoint URL directly to the mcps array when defining your Agent. CrewAI natively handles the HTTP transport and exposes all five air quality tools to that specific agent.

Import MCPServerHTTP from crewai.mcp and use the tool_filter parameter. You give your researcher agent access to get_city_feed while preventing it from touching get_ip_feed.

The framework's shared memory system handles this automatically. Once an agent pulls the JSON from get_station_feed, the exact pollutant metrics become available to the rest of the crew for subsequent tasks.

You structure the execution flow in your crew setup. One task tells an agent to run search_stations, and the strictly dependent next task forces another agent to analyze those specific results.

Your city name queries and IP addresses exist strictly within our ephemeral V8 sandboxes. Vinkius drops all network logs and memory states immediately after the text search resolves back to your Python environment.

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