How to Use the Ninox MCP in AutoGen

Q: How do my AutoGen agents access Ninox MCP tools?

Install autogen-extmcp and use the mcpservertools helper to fetch the tool definitions. Pass these tools to your assistant agents during setup, and the adapter will handle schema conversion automatically.

Q: Can one AutoGen agent read Ninox tables while another writes?

Yes. You can assign listrecords to an analyst agent and createrecords to a writer agent. They will collaborate via text to verify data before committing any changes.

Q: How does AutoGen handle errors from Ninox script executions?

If executeninoxscript returns an error, the executing agent shares the trace with the developer agent. They discuss the syntax error and generate a corrected script to try again.

Coordinate multi-agent debates to validate and write relational database updates to Ninox using AutoGen.

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 AutoGen

Create your Vinkius account to connect Ninox to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate database structures through AutoGen conversations

The `get_database_schema` tool provides your database structure to your AutoGen agents via the MCP Server. A schema auditor agent can analyze this structure and debate with a writer agent about the safest way to insert new records. This collaborative check ensures that your agents never attempt to write to invalid fields. They resolve structural conflicts before executing any tools, keeping your tables clean.

Run consensus-driven database updates via MCP Server

The `update_record` tool writes verified changes back to your tables after your agents reach a consensus. A performance agent and a security agent can debate the impact of the update before executing it. Once both agents agree the payload is safe, the writer agent executes `create_records` to commit the data. This multi-agent verification prevents bad data from corrupting your production databases.

Safe custom script execution via agent debate

The `execute_ninox_script` tool runs complex queries on your database backend. An analyst agent can write the script, while a security agent reviews the code for potential injection risks or infinite loops. Only after the security agent approves the code does the executor run the tool. This keeps your runtime environment secure while still allowing powerful database operations.

Setup guide

Set up Ninox MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Ninox tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Ninox_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Ninox data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Ninox_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Ninox data")
    print(result.messages[-1].content)

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 AutoGen

Install `autogen-ext[mcp]` and use the `mcp_server_tools` helper to fetch the tool definitions. Pass these tools to your assistant agents during setup, and the adapter will handle schema conversion automatically.

Yes. You can assign `list_records` to an analyst agent and `create_records` to a writer agent. They will collaborate via text to verify data before committing any changes.

If `execute_ninox_script` returns an error, the executing agent shares the trace with the developer agent. They discuss the syntax error and generate a corrected script to try again.

Yes. The Vinkius MCP Server supports both stdio and streamable HTTP transports, letting you configure your AutoGen environment to match your security requirements.

Your scripts are executed in an isolated V8 sandbox. Vinkius secures the session tokens ephemerally, ensuring that even if agents debate script logic, your core database credentials remain hidden.

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