How to Use the SketricGen MCP in OpenAI Agents SDK

Q: How do I manage agent communication with SketricGen using the OpenAI Agents SDK?

You initiate multi-agent sequences by calling runworkflow. The MCP Server handles passing data between agents automatically. Your client simply triggers the process, and the system manages the handoffs.

Q: What kind of history can SketricGen provide when using the OpenAI Agents SDK?

You can list and retrieve execution traces via listtraces or gettrace. This gives you a complete audit trail. It tells you exactly which tools ran, in what order, and what data was passed at each step.

Manage multi-agent operations with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect SketricGen to OpenAI Agents SDK — 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Run Complex Workflows

You kick off an entire operational sequence using `run_workflow`. This tool lets your agent call multiple specialized agents in a specific order, passing data between them. It's perfect for complex processes where one step depends on the output of another. Because you're building production systems with the OpenAI Agents SDK, every action is traced and validated against guardrails before it runs. You get full visibility into what happens at each handoff.

Maintain Agent State

Need to track who did what? Use `list_agents` or `get_agent` to pull agent details and capabilities. This lets your system know exactly which specialized agents are available in the MCP Server pool. You can then use this information to route tasks correctly. If you need a human reference point, `list_contacts` lets your client fetch contact lists, ensuring that any workflow targeting a person uses verified data.

Debug Execution Paths

When things break, you don't want guesswork. Call `get_trace` to get detailed execution logs for any failed or successful run. You can even check resource limits using `get_trace_credits`. This gives your development team the specific context needed to fix race conditions. Furthermore, `list_traces` lets you see a history of past runs, helping you compare current failures against previous successes and pinpoint exactly where the logic went sideways.

Setup guide

Set up SketricGen MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all SketricGen tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives SketricGen tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate SketricGen tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="SketricGen Agent",
            instructions="You have access to SketricGen tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You initiate multi-agent sequences by calling `run_workflow`. The MCP Server handles passing data between agents automatically. Your client simply triggers the process, and the system manages the handoffs.

You can list and retrieve execution traces via `list_traces` or `get_trace`. This gives you a complete audit trail. It tells you exactly which tools ran, in what order, and what data was passed at each step.

Absolutely. You can manage context by listing or getting specific `knowledge_bases` using `list_knowledge_bases` and `get_knowledge_base`. This ensures your agents pull information from approved, central sources.

While the primary validation is built into the OpenAI SDK guardrails, you can verify tool results by checking `get_conversation` details. This ensures the final output structure matches expectations before proceeding.

SketricGen manages conversation history, which is stored as conversational data that can be explicitly deleted with `delete_conversation`. This allows you to maintain strict control over client data retention.

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