How to Use the Flowise MCP in CrewAI

Q: How do I restrict which Flowise tools a specific CrewAI agent can use?

You use the MCPServerHTTP class from CrewAI's MCP toolset and apply a toolfilter. This lets you restrict access, ensuring a junior agent can only run listchatflows while only the moderator agent can invoke predict.

Q: Can CrewAI agents share memory across Flowise execution sessions?

Yes, you use gethistory to retrieve past chat execution logs and feed them into CrewAI's shared memory. This allows different agents on the team to maintain context across separate visual flow runs.

Q: How do I configure multiple Flowise MCP servers for a single CrewAI team?

You pass multiple URLs in the mcps list when initializing your CrewAI agents. Each agent can connect to different Flowise instances, allowing them to run predict across separate development and production environments.

Coordinate specialized CrewAI agent teams to monitor, run, and audit your visual Flowise pipelines autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flowise MCP to CrewAI

Create your Vinkius account to connect Flowise 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 Flowise with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign visual flows to specialized CrewAI agents

The `predict` tool lets your specialized research or analysis agents trigger complex visual workflows as part of their collaborative tasks. Instead of running a single linear prompt, an agent can hand off complex data processing to your low-code backend. This setup fits perfectly into sequential or hierarchical execution patterns. You pass the connection URL directly in the agent's `mcps` array, allowing them to invoke the tool whenever their role requires visual pipeline execution.

Map visual configurations via the Flowise MCP Server

The `list_chatflows` tool exposes all active visual pipelines to your moderator agent. This agent acts as a dispatcher, analyzing incoming tasks and deciding which specialized Flowise chatflow is best suited to handle the request. By using this MCP server integration, you avoid hardcoding flow IDs into your Python scripts. Your crew dynamically adapts as you add, modify, or delete pipelines inside the visual editor.

Monitor and audit crew interactions

The `get_history` tool reads past session logs so your supervisor agent can audit the team's performance. The supervisor checks execution metrics to ensure that handoffs between CrewAI agents and Flowise backends are happening without errors. If the supervisor detects a failed run or a timeout, it can trigger an escalation task to a human developer. This gives you a reliable safety net for autonomous operations without requiring constant manual oversight.

Setup guide

Set up Flowise 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 Flowise tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You use the `MCPServerHTTP` class from CrewAI's MCP toolset and apply a `tool_filter`. This lets you restrict access, ensuring a junior agent can only run `list_chatflows` while only the moderator agent can invoke `predict`.

Yes, you use `get_history` to retrieve past chat execution logs and feed them into CrewAI's shared memory. This allows different agents on the team to maintain context across separate visual flow runs.

You pass multiple URLs in the `mcps` list when initializing your CrewAI agents. Each agent can connect to different Flowise instances, allowing them to run `predict` across separate development and production environments.

The integration supports stdio, SSE, and Streamable HTTP transports. This flexibility allows your Python crew to connect to the Flowise MCP server regardless of whether you are running locally or in a cloud environment.

Your visual chatflows and database credentials are never stored on the Vinkius platform. The `list_credentials` and `get_history` tools process data purely in memory inside an ephemeral, zero-trust V8 sandbox, sending it directly to your local Python execution context.

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