How to Use the ncScale MCP in CrewAI

Q: How do I limit which ncScale tools a CrewAI agent can access?

You use the MCPServerHTTP class from the crewai.mcp package and define a toolfilter. This lets you restrict an agent to harmless tools like listdashboards while blocking access to sensitive user directories.

Q: Is my ticket and log data secure when queried by CrewAI?

Your tickets and logs accessed via listtickets and listlogs are processed strictly in memory within an isolated V8 sandbox environment. No data is stored or cached on the hosting platform, keeping your operational history completely confidential.

Deploy an autonomous multi-agent crew using CrewAI to monitor and debug your ncScale no-code stack.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ncScale MCP to CrewAI

Create your Vinkius account to connect ncScale 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 ncScale with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative no-code response with CrewAI

One agent shouldn't have to do everything. With this MCP Server, you can set up a CrewAI team where a Monitor Agent constantly checks `list_alerts` while a Triage Agent uses `get_alert` to classify the severity of incoming system failures. Once classified, a Coordinator Agent can check `list_users` to find the right developer to assign to the issue. This split-responsibility model prevents alert fatigue and ensures critical failures get immediate attention.

Autonomous stack auditing crews

Build a specialized crew that runs deep audits on your no-code integrations using this MCP Server. An Auditor Agent calls `list_integrations` to map out your stack, while a Performance Agent queries `list_nodes` to identify sluggish elements in your Bubble or Make workflows. The agents share their findings in a common memory pool. Together, they compile a detailed report on system bottlenecks, identifying which specific nodes are causing lag without requiring manual developer oversight.

Automated ticket resolution agents

Speed up your support pipeline by letting a CrewAI team manage your internal tickets. A Support Agent pulls active issues using `list_tickets`, while a Debugging Agent searches through system logs using `list_logs` to find the root cause of the reported problem. The crew works sequentially to resolve the issue. Once the Debugging Agent identifies the error, the Support Agent updates the ticket status and notifies the team, closing the loop autonomously.

Setup guide

Set up ncScale 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 ncScale tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the server's HTTP or SSE URL directly into the agent's `mcps` parameter during initialization. This instantly exposes tools like `list_alerts` and `list_logs` to that specific agent.

Yes, CrewAI agents share tools across the crew. This MCP integration lets a monitoring agent read active issues using `list_alerts` while a debugging agent concurrently pulls execution logs using `list_logs` to analyze the failure.

You use the `MCPServerHTTP` class from the `crewai.mcp` package and define a `tool_filter`. This lets you restrict an agent to harmless tools like `list_dashboards` while blocking access to sensitive user directories.

The crew's shared memory allows agents to retain context across different tool calls. If an agent calls `get_node` and finds an error, other agents can access that node's history when analyzing subsequent logs.

Your tickets and logs accessed via `list_tickets` and `list_logs` are processed strictly in memory within an isolated V8 sandbox environment. No data is stored or cached on the hosting platform, keeping your operational history completely confidential.

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