How to Use the PurpleAir MCP in CrewAI

Q: Can CrewAI agents share PurpleAir data with each other?

Yes. CrewAI agents use shared memory to pass outputs from getsensordata to downstream agents. For example, a researcher agent gets the raw PM2.5 values, and an analyst agent processes them.

Q: How do I restrict CrewAI to only query specific PurpleAir sensors?

Use the showonly parameter in listsensors or query specific indices using getsensorsbyindex. This keeps your agents focused on your specific hardware and prevents unnecessary API usage.

Q: Does this MCP Server support both indoor and outdoor monitors?

Yes. You can query indoor hardware using getindoorsensors or track ambient environment conditions using getoutdoorsensors depending on your operational needs.

Deploy specialized CrewAI agent teams to monitor PurpleAir sensors and coordinate industrial safety actions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PurpleAir MCP to CrewAI

Create your Vinkius account to connect PurpleAir to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PurpleAir with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Multi-Agent Air Quality Audits with CrewAI

Your CrewAI safety team uses `get_indoor_sensors` to run continuous indoor workspace health checks. A dedicated monitor agent pulls raw data, while an analyst agent compares those readings against OSHA guidelines to flag indoor air hazards. The crew coordinates these tasks using shared memory, passing sensor indices from `get_sensors_by_index` between agents. This team-based approach ensures that high PM2.5 levels trigger immediate, coordinated escalation plans.

Regional Wildfire Smoke Tracking

This MCP Server allows your CrewAI agents to track active wildfire plumes using `get_sensors_by_bounding_box`. A spotter agent scans the perimeter coordinates, while a reporter agent compiles real-time updates for regional teams. The agents use `get_pm25_sensors` to track the exact speed and direction of rising particulate matter. This allows the crew to predict which local outdoor spaces will require safety warnings hours before the smoke arrives.

Autonomous MCP Server Maintenance Checks

Your CrewAI maintenance crew uses `list_sensors` to audit the operational status of your hardware network. A diagnostic agent filters the list by `modified_since` to isolate sensors that haven't updated their readings recently. Once isolated, a second agent runs `get_sensor_data` on those specific indices to verify if the hardware is offline or just experiencing temporary network lag. The crew then generates a clean maintenance ticket without human intervention.

Setup guide

Set up PurpleAir 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 PurpleAir tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent PurpleAir 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="PurpleAir Analyst",
        goal="Access and analyze PurpleAir data via MCP.",
        backstory="Expert analyst with direct PurpleAir access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent PurpleAir 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 PurpleAir. 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 PurpleAir 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 PurpleAir MCP in CrewAI

Pass your Vinkius HTTP URL to the agent's MCP list during initialization. The agent automatically discovers tools like `get_sensors_near_me` and uses them to find the closest active monitors.

Yes. CrewAI agents use shared memory to pass outputs from `get_sensor_data` to downstream agents. For example, a researcher agent gets the raw PM2.5 values, and an analyst agent processes them.

All communication between your CrewAI framework and the Vinkius MCP Server runs over an encrypted, token-authorized HTTPS connection. Your custom sensor indices and local PM2.5 readings are never cached or exposed to third parties.

Use the `show_only` parameter in `list_sensors` or query specific indices using `get_sensors_by_index`. This keeps your agents focused on your specific hardware and prevents unnecessary API usage.

Yes. You can query indoor hardware using `get_indoor_sensors` or track ambient environment conditions using `get_outdoor_sensors` depending on your operational needs.

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