How to Use the Ninox MCP in CrewAI

Q: How do I add the Ninox MCP server to a CrewAI agent?

You pass the MCP server URL directly into the mcps list when defining your CrewAI agent. The CrewAI agent instantly gains access to all Ninox database tools, including listdatabases and getdatabaseschema.

Q: Can multiple CrewAI agents use updaterecord in Ninox simultaneously?

Yes, multiple CrewAI agents can invoke updaterecord as they complete tasks. CrewAI manages the execution order sequentially or hierarchically depending on your crew's Ninox database updates configuration.

Q: What happens if a CrewAI agent encounters an unknown schema in Ninox?

The CrewAI agent will automatically call getdatabaseschema to learn the Ninox table structures and field types. This dynamic discovery allows the CrewAI team to adapt to Ninox schema modifications without human intervention.

Deploy specialized teams of CrewAI agents to manage, audit, and update your Ninox database tables autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ninox MCP to CrewAI

Create your Vinkius account to connect Ninox 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 Ninox with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Database Auditing with the MCP Server

`list_records` lets your CrewAI auditor agent pull raw data from Ninox tables to check for inconsistencies. A second supervisor agent in your CrewAI team then reviews these Ninox findings before any modifications occur.

Collaborative Record Creation in CrewAI

`create_records` executes in Ninox after a planning CrewAI agent drafts the content and an editor agent approves it. This collaborative pipeline ensures that only high-quality, structured information enters your Ninox workspace via CrewAI.

Automated Script Execution for Team Decisions

`execute_ninox_script` runs complex relational calculations to provide your CrewAI team with real-time Ninox operational context. The CrewAI agents use the numeric or text outputs from Ninox to make autonomous decisions about task routing.

Setup guide

Set up Ninox 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 Ninox tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

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

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

You pass the MCP server URL directly into the `mcps` list when defining your CrewAI agent. The CrewAI agent instantly gains access to all Ninox database tools, including `list_databases` and `get_database_schema`.

Yes, multiple CrewAI agents can invoke `update_record` as they complete tasks. CrewAI manages the execution order sequentially or hierarchically depending on your crew's Ninox database updates configuration.

You can restrict CrewAI agent permissions by using a custom tool filter to exclude `delete_record` from the exposed tool list. This ensures your CrewAI team can only read and update Ninox data without risking accidental deletions.

The CrewAI agent will automatically call `get_database_schema` to learn the Ninox table structures and field types. This dynamic discovery allows the CrewAI team to adapt to Ninox schema modifications without human intervention.

Your Ninox record data and custom scripts are processed purely in-memory within your local CrewAI execution environment. The MCP server establishes a direct, zero-trust connection, ensuring no Ninox database payloads are cached or exposed to third-party monitoring services.

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