How to Use the Inworld AI MCP in CrewAI

Q: How do I connect Inworld AI to my CrewAI agents?

Pass the server URL directly into the mcps parameter of your Agent configuration. CrewAI automatically handles the tool registration.

Q: How do I limit which Inworld AI tools my CrewAI agents can use?

Use the toolfilter in your agent definition. This lets you restrict access to specific operations like voice synthesis or router management.

Deploy a crew of specialized AI agents that use Inworld AI for lifelike, multi-agent collaboration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Inworld AI MCP to CrewAI

Create your Vinkius account to connect Inworld AI 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 Inworld AI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent voice collaboration in CrewAI

Assign different voices to different agents in your crew using `get_voice`. This allows your research, analysis, and moderator agents to sound distinct during their collaborative sessions. Your crew can synthesize their findings into audio output using `synthesize_speech_sync`. It makes autonomous reporting much more effective.

Autonomous character orchestration

Let your CrewAI agents manage their own character routers. They can use `list_routers` to find the right persona for a task and `update_router` to adjust their behavior based on the current mission. This is great for autonomous operations where an agent might need to switch from a research persona to a critical feedback persona. It happens without human intervention.

Transcription for agent feedback loops

Feed audio data back into your crew by using `transcribe_audio`. Your agents can listen to user input, transcribe it into text, and then decide on the next action. This closes the loop between human input and agent response. It is the foundation for a truly hands-off operational setup.

Setup guide

Set up Inworld AI 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 Inworld AI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

Pass the server URL directly into the `mcps` parameter of your Agent configuration. CrewAI automatically handles the tool registration.

Yes. You can give each agent in your crew access to the Inworld AI MCP server. They can each call their own tools independently.

Use the `tool_filter` in your agent definition. This lets you restrict access to specific operations like voice synthesis or router management.

It is. You can set up a moderator agent that watches the conversation and triggers audio alerts or transcriptions when specific conditions are met.

Your audio transcripts and voice synthesis requests are processed within your workspace. Only the data you explicitly pass to the agents is handled during the session.

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