How to Use the Nhost MCP in AutoGen

Q: How do I give Nhost tools to my AutoGen agents?

Use the autogen-extmcp package and its mcpservertools function. Point it to your Vinkius endpoint, and it returns a list of tools you can pass directly to an AssistantAgent during initialization.

Q: Can different AutoGen agents have different permissions for the Nhost MCP server?

Yes. You can call mcpservertools multiple times with a filter to create different toolsets. Then, assign the 'storage' tools to one agent and the 'auth' tools to another, forcing them to collaborate.

Equip your AutoGen agents to debate and execute Nhost operations. One agent can propose a user action, another can validate it before running.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nhost MCP to AutoGen

Create your Vinkius account to connect Nhost 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 Nhost with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Auth Flows Before Execution

This isn't about one agent blindly calling tools. You can set up a conversation where a 'user proxy' agent suggests signing up a new user, and a 'security' agent confirms that using `signup_email_password` is the right tool for the job. The agents reach a consensus before any action is taken. This prevents errors and ensures the correct Nhost authentication flow is chosen, whether it's `signin_otp_email` for quick access or a full password-based login.

Isolate Actions Between Agents

Assign different Nhost tools to different agents to enforce separation of duties. For example, give your 'storage manager' agent access to `upload_file` and `delete_file`, but restrict your 'user admin' agent to only `get_user` and `reset_password`. This mirrors real-world team permissions. The conversation between agents becomes a log of who did what and why, because one agent has to explicitly ask another to perform an action it can't do itself. This is a core strength of using this MCP server with AutoGen.

Build a Multi-Agent AutoGen DevOps Team

Create a team of agents to manage your Nhost backend. One agent could be tasked with onboarding new users via `signup_otp_email`, while another's job is to generate temporary access links using `get_file_presigned_url` for support tickets. They don't just execute; they coordinate. The 'onboarding' agent can notify the 'support' agent when a new user is created, triggering the next step in a complex, automated workflow.

Setup guide

Set up Nhost 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 Nhost 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="Nhost_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Nhost 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="Nhost_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Nhost 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 Nhost. 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 Nhost 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 Nhost MCP in AutoGen

Use the `autogen-ext[mcp]` package and its `mcp_server_tools` function. Point it to your Vinkius endpoint, and it returns a list of tools you can pass directly to an `AssistantAgent` during initialization.

Yes. You can call `mcp_server_tools` multiple times with a filter to create different toolsets. Then, assign the 'storage' tools to one agent and the 'auth' tools to another, forcing them to collaborate.

A user proxy might say, 'I need to log in.' An assistant agent could reply, 'Okay, I will use the `signin_email_password` tool. Please provide your credentials.' The tool execution and result are part of the chat history.

Absolutely. You can build an agent whose sole purpose is to respond to requests like 'Create a new anonymous user' by calling `signin_anonymous` or 'Log me out everywhere' by executing `signout`.

The conversation history itself becomes a key security area. Since agents pass credentials or session tokens in their messages to execute tools like `signin_email_password`, you must secure the chat logs. The Vinkius MCP server is isolated, but the data flows through the agent discussion.

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