How to Use the Activepieces MCP in CrewAI

Q: How do I prevent a CrewAI agent from deleting Activepieces flows?

Use the toolfilter parameter when configuring the HTTP server class. Simply exclude deleteflow and deleteproject from the allowed list. The agent will not even know those commands exist.

Q: Are my Activepieces internal table records safe when using this MCP Server?

Tools like listrecords pull raw rows from your internal data tables, which often include user PII or financial metrics. The Vinkius architecture processes these requests through a stateless proxy that retains absolutely zero context. Your proprietary database entries pass through the system without ever touching persistent disk storage.

Deploy specialized CrewAI agents to monitor, debug, and configure your Activepieces infrastructure autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Activepieces MCP to CrewAI

Create your Vinkius account to connect Activepieces 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 Activepieces with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let agents fix broken automations

A dedicated debugging agent uses `get_flow_run` and `list_flow_runs` to investigate failures. Production automations break at 3 AM when APIs change or rate limits hit. Waiting for an engineer to wake up costs money. Your monitor agent notices a spike in errors and delegates the investigation to an analyzer. The analyzer reads the raw execution logs, identifies the faulty step, and proposes a fix. A separate moderator agent then reviews the solution before applying it.

Structure projects via MCP Server

Creating logical groupings for automations requires `create_folder` and `update_folder`. Messy environments slow down development teams as the number of workflows grows. An agent crew can enforce naming conventions and sort items automatically. You assign a librarian agent the task of organizing the workspace. It pulls all assets using `list_flows`, checks their current locations, and moves them into appropriate directories. The entire cleanup process happens in the background without any manual dragging and dropping.

Sync settings across all flows

Admin agents control shared resources using `upsert_global_connection` and `delete_global_connection`. Updating a database password usually means manually editing dozens of individual workflows. Exposing global variables to your crew via an MCP connection makes sweeping changes trivial. When a core service rotates its API key, your security agent updates the global connection once. It then verifies the change by running a test flow. Hierarchical execution ensures the update finishes completely before the crew marks the task as resolved.

Setup guide

Set up Activepieces 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 Activepieces tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You can pass the Vinkius endpoint URL directly into the mcps array when defining your agent. For more granular control, import MCPServerHTTP from crewai.mcp. This advanced method lets you filter specific tools for different roles.

Yes, you can assign the server to multiple agents within your crew. A researcher might only use list_projects, while an executor holds permissions for update_project. They collaborate using shared memory to accomplish complex tasks.

The underlying transport supports stdio, SSE, and Streamable HTTP. CrewAI handles the communication layer automatically. Your agents will receive the tool execution results as soon as the platform returns them.

Use the tool_filter parameter when configuring the HTTP server class. Simply exclude delete_flow and delete_project from the allowed list. The agent will not even know those commands exist.

Tools like list_records pull raw rows from your internal data tables, which often include user PII or financial metrics. The Vinkius architecture processes these requests through a stateless proxy that retains absolutely zero context. Your proprietary database entries pass through the system without ever touching persistent disk storage.

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