How to Use the Sproof MCP in AutoGen

Q: Can I use AutoGen to manage multiple documents with Sproof?

Yes. One agent can list all necessary files using listdocuments, and another can then iterate through that list, calling getdocument for each one to gather data.

Q: Is there a way to cancel requests with Sproof and AutoGen?

You use the cancelsignaturerequest tool. The agents can debate whether cancellation is appropriate, comparing it against historical logs retrieved via listaudittrail.

Q: What data types does Sproof touch when using AutoGen?

The server handles user account profiles (getprofile), contact records, and the complex state of ongoing signature requests. This is all used as conversational evidence.

Facilitate consensus-driven decisions with AutoGen and Sproof's 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 Sproof MCP to AutoGen

Create your Vinkius account to connect Sproof 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 Sproof with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Signature Workflow Decisions for AutoGen

One agent can call `create_signature_request` to suggest a path forward. Another agent might challenge that decision by calling `get_document` to verify the required document type first. The agents debate which set of steps is necessary before proceeding, leading to a consensus on the final action.

Automated Contact Verification with AutoGen MCP Server

A 'Compliance Agent' calls `list_contacts` and verifies every person listed. A 'Speed Agent' might argue they should just assume the contact is valid. The agents debate the risk level, converging on a final decision about whether or not to call `create_contact`. This simulates complex human deliberation entirely within your system.

Consensus-Driven Data Retrieval for AutoGen

If an agent needs details, it might initially call `list_signature_requests`. A second agent can then challenge that by asking for the full history using `list_audit_trail`. The debate continues until both agents agree on the most complete and accurate set of data needed to solve the user's core problem.

Setup guide

Set up Sproof 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 Sproof 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="Sproof_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You assign opposing roles to your agents. For example, one agent monitors compliance risks while another pushes for speed. Their debate over tools like `get_profile` determines the final outcome.

It processes structured and semi-structured data from every tool call. This includes document metadata, contact lists, and signature status updates that are used as evidence during the debate.

Yes. One agent can list all necessary files using `list_documents`, and another can then iterate through that list, calling `get_document` for each one to gather data.

You use the `cancel_signature_request` tool. The agents can debate whether cancellation is appropriate, comparing it against historical logs retrieved via `list_audit_trail`.

The server handles user account profiles (`get_profile`), contact records, and the complex state of ongoing signature requests. This is all used as conversational evidence.

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