How to Use the Autenti MCP in AutoGen

Q: How do I load Autenti tools into AutoGen?

Install autogen-extmcp first. Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius endpoint. Pass that list directly into your AssistantAgent constructor.

Q: How do agents handle process errors?

Errors become part of the chat history. If getprocessdetails returns a missing ID, the executing agent reports the failure to the group. The manager agent then instructs it to search listsignatureprocesses instead.

Let your AutoGen agents debate and manage eIDAS document signing flows through the Autenti MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Autenti MCP to AutoGen

Create your Vinkius account to connect Autenti 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 Autenti with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent contract negotiation

Single agents make mistakes. You can build a system where a legal agent drafts a document while a compliance agent verifies the signers. They use `list_saved_contacts` to cross-reference the address book before anyone hits send. Disagreements get resolved through conversation. If the compliance agent spots a missing observer, it demands the legal agent run `add_new_contact`. The contract only moves forward once both agents reach a consensus on the participant list.

Consensus-driven process execution

Firing off a legally binding agreement requires strict oversight. One agent proposes starting a flow via `create_new_signature_process`. A secondary security agent reviews the metadata and title for accuracy before approving the API call. Finding the right next step works the same way. The system runs `list_available_process_actions` to see what is legally permitted. The agents debate whether to send a reminder or reject the document, finally triggering `execute_process_action` when they agree.

Monitor the Autenti MCP Server

Background monitoring agents keep your systems healthy. You assign a dedicated watchdog agent to ping `check_api_health` on a schedule. If the connection drops, it alerts your operations team immediately. Another agent watches for incoming events. By checking `list_configured_webhooks`, it ensures your external systems are wired up correctly to receive signature completions. AutoGen turns static API management into an active, self-healing conversation.

Setup guide

Set up Autenti 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 Autenti 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="Autenti_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` first. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius endpoint. Pass that list directly into your `AssistantAgent` constructor.

They share the same tool definitions but execute independently. The `McpToolAdapter` converts the schema automatically for every agent in the chat. One agent can draft while another reviews.

Errors become part of the chat history. If `get_process_details` returns a missing ID, the executing agent reports the failure to the group. The manager agent then instructs it to search `list_signature_processes` instead.

No manual mapping is required. AutoGen reads the JSON-RPC tool definitions natively. Your agents immediately understand the parameters required for complex endpoints like the signature creation tool.

Every tool execution happens inside a secure, ephemeral V8 sandbox. Your agents might discuss confidential contract titles and participant names, but Vinkius stores none of it. Authentication is handled via a single endpoint token that never exposes your raw credentials.

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