How to Use the SketricGen MCP in AutoGen

Q: How does SketricGen help AutoGen manage debates?

SketricGen provides a set of reliable tools—like gettrace or listcontacts—that the agents use as facts during their debate. The answer they find has to be provable by invoking these MCP Server tools.

Q: Can I track agent communication when using SketricGen and AutoGen?

Yes, listtraces gives you a full history of the reasoning path. You can see which agents spoke, what tool they invoked, and why that action was necessary for their argument.

Q: What data does the MCP Server touch when using SketricGen and AutoGen?

The server manages agent identity (listagents), contact details, and conversation history. These are the core data points that multiple agents debate over and act upon.

Q: What if I need to clear out old discussion context with SketricGen and AutoGen?

You can use deleteconversation right after a major decision is reached. This keeps the system clean and prevents stale data from skewing future agent debates.

Get consensus decisions with AutoGen using SketricGen tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SketricGen MCP to AutoGen

Create your Vinkius account to connect SketricGen 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 SketricGen with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Consensus-Driven Decision Making

AutoGen excels when agents debate. You let one agent check the system status via `check_sketricgen_status`, while a second agent retrieves necessary contact details using `get_contact`. They then negotiate on the best workflow to run. This setup moves beyond simple tool calling; it requires deliberation between competing viewpoints, forcing the agents to converge on the right answer.

Multi-Agent Workflow Orchestration

The `run_workflow` tool is key here. Instead of one agent running a process solo, AutoGen lets multiple specialized agents feed inputs into it and argue over parameters. The system then executes the consensus plan. This structure solves problems where the answer isn't obvious and requires input from different perspectives.

System State Reporting

You can use `list_agents` to define who is arguing, or `get_agent` to give them a specific persona. Before the debate starts, agents pull context using `list_workflows`. This ensures every agent has the most current understanding of the system's capabilities. It keeps the discussion grounded in reality by providing clear access to system metadata.

Setup guide

Set up SketricGen 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 SketricGen 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="SketricGen_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

SketricGen provides a set of reliable tools—like `get_trace` or `list_contacts`—that the agents use as facts during their debate. The answer they find has to be provable by invoking these MCP Server tools.

Yes, `list_traces` gives you a full history of the reasoning path. You can see which agents spoke, what tool they invoked, and why that action was necessary for their argument.

The server manages agent identity (`list_agents`), contact details, and conversation history. These are the core data points that multiple agents debate over and act upon.

You can use `delete_conversation` right after a major decision is reached. This keeps the system clean and prevents stale data from skewing future agent debates.

It handles contact details, conversation logs, and agent credentials. When designing your multi-agent debate, always keep privacy concerns top of mind regarding this exposed data.

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