How to Use the Voiceflow MCP in CrewAI

Q: How can CrewAI agents query documentation using Voiceflow's MCP Server?

The crew uses the querykb tool. This allows a specialized research agent to search your full knowledge base and return actionable data that other agents can use.

Q: If I need to list available Voiceflow projects for my autonomous team, which tool should I pass to CrewAI?

Pass listprojects to the crew. This allows one of your specialized agents to scope the problem by listing all existing conversation flows in the system.

Q: Does Voiceflow support state management for advanced automation with CrewAI?

Yes, you use getstate and savestate. This mechanism lets your crew maintain a shared memory of user variables throughout complex, multi-agent operations.

Q: What tools are available to monitor conversation history in Voiceflow with CrewAI?

You can use listtranscripts and gettranscript. These tools provide the full context needed for a moderator agent to review past sessions or identify recurring issues.

Q: What data privacy information does this MCP Server touch?

This server touches user conversation state/variables and conversation transcripts. Since these are core inputs to the crew, treat them as sensitive operational data.

Build autonomous teams that run specialized conversational agents using CrewAI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Voiceflow MCP to CrewAI

Create your Vinkius account to connect Voiceflow 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 Voiceflow with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent tasks

The MCP Server exposes multiple tools, allowing your crew to delegate roles. One agent might use `list_projects` to research available flows, while another uses `query_kb` to find specific answers. The specialized nature of the tools means that Agent A doesn't need to know how Agent B operates; it just needs to hand off a clean result.

Maintain conversation memory across agents

Agents share context using `get_state` and updating variables via `save_state`. This ensures that even if the workflow involves five specialized steps, the core facts remain available to every member of the crew. The system can also track historical dialogue using `list_transcripts`, giving your monitor agent a full audit trail.

Handle immediate user input and feedback

When an interaction happens, the crew uses `interact` to send messages. They can then use `get_feedback` or check for specific project details with `get_project`. This keeps the loop tight between the human user and your autonomous system. The server also supports listing all potential projects via `list_projects`, letting your initial research agent scope the problem correctly.

Setup guide

Set up Voiceflow 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 Voiceflow tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

The crew uses the `query_kb` tool. This allows a specialized research agent to search your full knowledge base and return actionable data that other agents can use.

Pass `list_projects` to the crew. This allows one of your specialized agents to scope the problem by listing all existing conversation flows in the system.

Yes, you use `get_state` and `save_state`. This mechanism lets your crew maintain a shared memory of user variables throughout complex, multi-agent operations.

You can use `list_transcripts` and `get_transcript`. These tools provide the full context needed for a moderator agent to review past sessions or identify recurring issues.

This server touches *user conversation state/variables* and *conversation transcripts*. Since these are core inputs to the crew, treat them as sensitive operational data.

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