What smart home devices and apps are supported through Composio?

Composio provides access to 1000+ smart home tool integrations including Sensibo (climate control), Philips Hue (lighting), SmartThings (hub), and many more device ecosystems. Use `list_composio_tools` to discover all available tools, or `search_composio_tools` to find tools for specific apps or categories.

What's the difference between executing a tool with arguments vs. with text?

**With arguments** (`execute_composio_tool`): You provide a JSON object matching the tool's exact schema. This gives you precise control over every parameter. **With text** (`execute_composio_tool_with_text`): You provide natural language instructions like "turn on the AC to 72 degrees" and Composio's AI parses and maps it to the correct parameters. Use arguments for precision, text for convenience.

How do I get a Composio API key?

Visit https://app.composio.dev/ and sign up for a Composio account. Navigate to your API settings or developer dashboard to generate an API key (starts with `ak_`). The key gives you access to all available smart home tool integrations.

Do I need separate authentication for each smart home app?

No! Composio handles authentication to individual smart home services internally. You only need your Composio API key. However, you may need to connect your accounts to specific services through Composio's connection management first. Use the `connected_account_id` parameter when executing tools if you have multiple accounts connected.

Composio Smart Home MCP Server for CrewAI 8 tools — connect in under 2 minutes

Name: Composio Smart Home
Availability: InStock
Author: Vinkius

docs.crewai.com/mcp/overview

Built by Vinkius GDPR 8 Tools Framework

Connect your CrewAI agents to Composio Smart Home through the Vinkius — pass the Edge URL in the `mcps` parameter and every Composio Smart Home tool is auto-discovered at runtime. No credentials to manage, no infrastructure to maintain.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from crewai import Agent, Task, Crew

agent = Agent(
    role="Composio Smart Home Specialist",
    goal="Help users interact with Composio Smart Home effectively",
    backstory=(
        "You are an expert at leveraging Composio Smart Home tools "
        "for automation and data analysis."
    ),
    # Your Vinkius token — get it at cloud.vinkius.com
    mcps=["https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"],
)

task = Task(
    description=(
        "Explore all available tools in Composio Smart Home "
        "and summarize their capabilities."
    ),
    agent=agent,
    expected_output=(
        "A detailed summary of 8 available tools "
        "and what they can do."
    ),
)

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

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Composio Smart Home MCP Server

Connect to Composio API and control smart home devices across 1000+ integrations through structured JSON arguments or natural language commands. Composio abstracts away authentication and API complexity, giving AI agents a unified interface to control Sensibo, Philips Hue, SmartThings, and hundreds of other smart home ecosystems.

When paired with CrewAI, Composio Smart Home becomes a first-class tool in your multi-agent workflows. Each agent in the crew can call Composio Smart Home tools autonomously — one agent queries data, another analyzes results, a third compiles reports — all orchestrated through the Vinkius with zero configuration overhead.

What you can do

Tool Discovery — List and search all available smart home tools across Composio's extensive integration catalog
Schema Inspection — View complete parameter schemas for any tool before executing it
Structured Execution — Execute tools with precise JSON arguments matching each tool's schema
Natural Language Control — Execute tools using conversational English — Composio's AI parses and maps parameters automatically
App-Specific Tools — Browse all available actions for specific smart home apps like Sensibo, Philips Hue, etc.
Multi-Device Control — Access tools for climate control, lighting, security, entertainment, and more
Unified Interface — One API key gives access to 1000+ smart home integrations without individual auth setup

The Composio Smart Home MCP Server exposes 8 tools through the Vinkius. Connect it to CrewAI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Composio Smart Home to CrewAI via MCP

Follow these steps to integrate the Composio Smart Home MCP Server with CrewAI.

Install CrewAI

Run pip install crewai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Customize the agent

Adjust the role, goal, and backstory to fit your use case

Run the crew

Run python crew.py — CrewAI auto-discovers 8 tools from Composio Smart Home

Why Use CrewAI with the Composio Smart Home MCP Server

CrewAI Multi-Agent Orchestration Framework provides unique advantages when paired with Composio Smart Home through the Model Context Protocol.

Multi-agent collaboration lets you decompose complex workflows into specialized roles — one agent researches, another analyzes, a third generates reports — each with access to MCP tools

CrewAI's native MCP integration requires zero adapter code: pass the Vinkius Edge URL directly in the `mcps` parameter and agents auto-discover every available tool at runtime

Built-in task delegation and shared memory mean agents can pass context between steps without manual state management, enabling multi-hop reasoning across tool calls

Sequential and hierarchical crew patterns map naturally to real-world workflows: enumerate subdomains → analyze DNS history → check WHOIS records → compile findings into actionable reports

Composio Smart Home + CrewAI Use Cases

Practical scenarios where CrewAI combined with the Composio Smart Home MCP Server delivers measurable value.

Automated multi-step research: a reconnaissance agent queries Composio Smart Home for raw data, then a second analyst agent cross-references findings and flags anomalies — all without human handoff

Scheduled intelligence reports: set up a crew that periodically queries Composio Smart Home, analyzes trends over time, and generates executive briefings in markdown or PDF format

Multi-source enrichment pipelines: chain Composio Smart Home tools with other MCP servers in the same crew, letting agents correlate data across multiple providers in a single workflow

Compliance and audit automation: a compliance agent queries Composio Smart Home against predefined policy rules, generates deviation reports, and routes findings to the appropriate team

Composio Smart Home MCP Tools for CrewAI (8)

These 8 tools become available when you connect Composio Smart Home to CrewAI via MCP:

execute_composio_tool

Execute a Composio smart home tool with structured JSON arguments

execute_composio_tool_with_text

Execute a Composio smart home tool using a natural language instruction

execute_multiple_composio_tools

Provide tool_slug with either arguments (JSON) or text (natural language) per item. Execute multiple Composio smart home tools in a single sequential request

get_composio_tool_schema

Retrieve the full JSON schema and accepted parameters for a specific Composio tool

list_app_tools

List all available tools for a specific smart home app integration

list_composio_tools

List all available smart home tools and integrations in Composio

list_connected_accounts

List all connected smart home accounts and integrations in Composio

search_composio_tools

Search for smart home tools by app slug or category keyword

Example Prompts for Composio Smart Home in CrewAI

Ready-to-use prompts you can give your CrewAI agent to start working with Composio Smart Home immediately.

"List all available smart home tools I can execute."

"Turn on my living room AC and set it to 22°C."

"Show me all tools available for Sensibo."

Troubleshooting Composio Smart Home MCP Server with CrewAI

Common issues when connecting Composio Smart Home to CrewAI through the Vinkius, and how to resolve them.

MCP tools not discovered

Ensure the Edge URL is correct. CrewAI connects lazily when the crew starts — check console output.

Agent not using tools

Make the task description specific. Instead of "do something", say "Use the available tools to list contacts".

Timeout errors

CrewAI has a 10s connection timeout by default. Ensure your network can reach the Edge URL.

Rate limiting or 429 errors

The Vinkius enforces per-token rate limits. Check your subscription tier and request quota in the dashboard. Upgrade if you need higher throughput.

Composio Smart Home + CrewAI FAQ

Common questions about integrating Composio Smart Home MCP Server with CrewAI.

How does CrewAI discover and connect to MCP tools?

CrewAI connects to MCP servers lazily — when the crew starts, each agent resolves its MCP URLs and fetches the tool catalog via the standard tools/list method. This means tools are always fresh and reflect the server's current capabilities. No tool schemas need to be hardcoded.

Can different agents in the same crew use different MCP servers?

Yes. Each agent has its own mcps list, so you can assign specific servers to specific roles. For example, a reconnaissance agent might use a domain intelligence server while an analysis agent uses a vulnerability database server.

What happens when an MCP tool call fails during a crew run?

CrewAI wraps tool failures as context for the agent. The LLM receives the error message and can decide to retry with different parameters, fall back to a different tool, or mark the task as partially complete. This resilience is critical for production workflows.

Can CrewAI agents call multiple MCP tools in parallel?

CrewAI agents execute tool calls sequentially within a single reasoning step. However, you can run multiple agents in parallel using process=Process.parallel, each calling different MCP tools concurrently. This is ideal for workflows where separate data sources need to be queried simultaneously.

Can I run CrewAI crews on a schedule (cron)?

Yes. CrewAI crews are standard Python scripts, so you can invoke them via cron, Airflow, Celery, or any task scheduler. The crew.kickoff() method runs synchronously by default, making it straightforward to integrate into existing pipelines.