How to Use the SuperTokens MCP in AutoGen

Q: How does SuperTokens function in AutoGen's debate process?

The MCP server provides specific, atomic tools (like signinuser or signupuser) that agents can call to advance the conversation and test different hypotheses.

Q: Can I use SuperTokens to validate state in AutoGen conversations?

Yes. You can call getuser at various points in the debate. This allows one agent to check the current ground truth of the user before another proposes a change.

Drive consensus decisions for AutoGen agents using SuperTokens' identity tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SuperTokens MCP to AutoGen

Create your Vinkius account to connect SuperTokens to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SuperTokens with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debating User Access with AutoGen

Use the server to simulate a decision process. One agent can propose an action, say `assign_role_to_user`, while another acts as a security guard using `list_user_roles` to challenge the request. The agents debate until they reach consensus on whether the role change is appropriate and safe.

Modeling Account Changes for AutoGen

When complex identity changes are needed, multiple agents can weigh in. One agent might recommend `link_accounts`, while another calls `get_user` to verify the current state before proceeding. The negotiation framework forces the model to consider preconditions, making the final action highly reliable.

Conflict Resolution with MCP Server

Agents can resolve disputes over user status. For example, Agent A wants to delete a session (`remove_session`), but Agent B first calls `get_user` to confirm the user still exists. The multi-agent system forces validation across multiple tool boundaries before any irreversible action occurs.

Setup guide

Set up SuperTokens 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 SuperTokens 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="SuperTokens_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The MCP server provides specific, atomic tools (like `signin_user` or `signup_user`) that agents can call to advance the conversation and test different hypotheses.

It's perfect for scenarios where an action requires consensus, like deciding whether a user has enough privileges based on their roles before creating a new resource.

Yes. You can call `get_user` at various points in the debate. This allows one agent to check the current ground truth of the user before another proposes a change.

The server manages fundamental identity records, including roles, sessions, and associated metadata. These are the pieces of information agents debate over.

Agents can simulate full lifecycles: a new account is created via `signup_user`, roles are assigned, and sessions are maintained or revoked during the multi-agent conversation.

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