How to Use the Authing MCP in AutoGen

Q: How do I hook up Authing to AutoGen via MCP?

Grab the autogen-extmcp package via pip. Use mcpservertools with a StreamableHttpServerParams object pointing to your endpoint. Pass the returned list directly into your AssistantAgent constructor.

Q: Do AutoGen agents understand the Authing tool schemas?

The McpToolAdapter translates the protocol definitions into native JSON schemas automatically. Your agents instantly know what arguments the directory API expects. No manual type mapping is necessary.

Deploy multi-agent debates over identity governance by connecting Authing to AutoGen for consensus-driven administration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Authing MCP to AutoGen

Create your Vinkius account to connect Authing 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 Authing with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Provisioning Debates

Triggering the `create_user` tool happens only after your agents reach an agreement. A compliance agent reviews the requested access level while an IT agent checks group capacity. They argue over the exact parameters until both approve the final payload. You set up this dynamic to prevent single-point failures in human judgment. The system runs the MCP protocol's `list_roles` to verify available permissions before any write operation executes. This consensus-driven approach catches misconfigurations before they hit your production directory.

Real-time Authing MCP Server Threat Analysis

Monitoring access patterns requires agents to constantly poll `get_audit_logs` and `get_security_settings`. One agent flags a spike in failed logins from a specific IP. A secondary agent analyzes the current password policy to determine if a brute-force attack is viable. They negotiate the severity of the threat in real time. If they decide the risk is critical, they can formulate a response plan or alert a human admin. You build a security operations center out of competing AI perspectives.

Directory Architecture Reviews

Auditing your organizational structure involves running `list_organizations` and `list_groups` to map the hierarchy. Your architect agent suggests flattening the group structure to reduce complexity. The security agent pushes back, arguing that granular groups isolate risk better. Finding unregistered shadow IT is another use case where `list_applications` proves valuable. The agents cross-reference registered apps against known vendor contracts. The resulting output is a heavily vetted recommendation, not just a raw data dump.

Setup guide

Set up Authing 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 Authing 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="Authing_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Grab the `autogen-ext[mcp]` package via pip. Use `mcp_server_tools` with a `StreamableHttpServerParams` object pointing to your endpoint. Pass the returned list directly into your `AssistantAgent` constructor.

The `McpToolAdapter` translates the protocol definitions into native JSON schemas automatically. Your agents instantly know what arguments the directory API expects. No manual type mapping is necessary.

You pass the same tool list to any agent that needs directory access. The framework handles routing the execution requests through the single transport layer. They can all read the same audit logs simultaneously.

The integration supports both standard input/output and Streamable HTTP connections. You pick the transport based on whether your agents run locally or in a distributed cloud environment.

Requesting application lists or user profiles routes through a heavily isolated V8 sandbox on Vinkius. The execution environment holds no memory of the transaction after the HTTP response completes. Your multi-agent conversations retain the context, but the connection layer remains entirely stateless and secure.

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