How to Use the Cartesia (Voice AI) MCP in CrewAI

Give your CrewAI agents the ability to clone voices, transcribe calls, and generate speech autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cartesia (Voice AI) MCP to CrewAI

Create your Vinkius account to connect Cartesia (Voice 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 Cartesia (Voice AI) with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous call analysis

Set up a monitor agent to watch your voice bots. It calls `list_agent_calls` to pull the latest transcripts from your active sessions. An analyst agent then reviews those transcripts for compliance. If the audio is missing, it triggers `stt_batch` to generate the text from the raw recordings.

Multi-agent voice generation

One agent writes the script. Another agent calls `tts_bytes` to turn that script into actual audio files. They pass the results through shared memory. When the target audience changes, a localization agent jumps in. It runs `localize_voice` to adapt the generated speech into Spanish or French without human input.

Cartesia MCP Server dictionary control

Specialized crews need specialized vocabularies. Your setup agent uses `create_pronunciation_dict` before the main workflow even starts. After the project finishes, a cleanup agent runs `delete_pronunciation_dict` to keep the workspace tidy. The entire lifecycle happens automatically.

Setup guide

Set up Cartesia (Voice 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 Cartesia (Voice AI) tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

    task = Task(
        description="List recent Cartesia (Voice 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 Cartesia. 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 Cartesia (Voice 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 Cartesia (Voice AI) MCP in CrewAI

The fastest way is passing the Vinkius URL into the agent's `mcps` array. For tighter control over which agent gets what, use `MCPServerHTTP` with a `tool_filter`.

They do. Just assign the MCP connection at the crew level, and your agents will negotiate who calls the transcription or generation endpoints based on their roles.

Assign a specific agent to language adaptation. It will use the localization tool to modify existing voice profiles autonomously based on the crew's current objective.

Yes. A billing agent can periodically call the usage credits tool and alert you if the crew is burning through your budget too fast.

We isolate every connection. The text transcripts and batch STT audio segments route through a secure sandbox and vanish the second your agent finishes processing them.

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