How to Use the DecileHub MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle tracing for DecileHub tool calls?

Every tool invocation, such as running listinvestors, is logged directly to your OpenAI developer dashboard. You can inspect the exact tool inputs, outputs, and model reasoning steps in real-time.

Run safe, production-grade venture portfolio queries directly inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DecileHub MCP to OpenAI Agents SDK

Create your Vinkius account to connect DecileHub to OpenAI Agents SDK 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 DecileHub with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe LP data lookups with OpenAI Agents SDK

Your production agents can now safely query investor profiles using `list_investors` and `get_investor` without manual data exports over this MCP Server connection. The SDK's built-in guardrails validate every single parameter before your agent attempts to fetch sensitive LP commitments, preventing bad tool calls from crashing your pipeline. Tracing these operations on the OpenAI dashboard lets you see exactly how the model reasons about fund performance before returning data to your team. If an agent tries to fetch private investor details, the runtime halts the execution, keeping your LP records protected.

Automated fund performance checks

Let specialized agents hand off tasks to each other when analyzing fund health. One agent can pull the high-level performance numbers using `get_fund_performance`, then pass the raw metrics to a financial analyst agent that runs deeper valuation checks. This MCP Server exposes `list_funds` and `get_fund` to give your OpenAI Agents SDK setup direct access to your venture metrics. You configure it once in your Python code, and the agents dynamically discover the tools.

Portfolio valuation and filing analysis

Agents can monitor portfolio health by calling `list_portfolio_companies` and `get_company` to flag valuation changes. When a new SEC filing drops, the agent uses `list_filings` to pull the latest reports. This MCP Server exposes `list_valuations` and `get_filing_report` directly to your OpenAI Agents SDK runtime. Your agent handles the heavy lifting, analyzing the documents and mapping the new valuations without manual data entry.

Setup guide

Set up DecileHub 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 DecileHub tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate DecileHub 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="DecileHub Agent",
            instructions="You have access to DecileHub 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 Decile Hub. 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 DecileHub 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 DecileHub MCP in OpenAI Agents SDK

You pass the Vinkius HTTP endpoint directly to the MCPServerStreamableHttp constructor in your Python code. Once you add it to your agent's server list, the SDK automatically discovers tools like get_fund_performance at startup.

Yes, you handle this by setting up guardrails in your Python agent definitions. You can block agents from calling write-heavy or sensitive tools like list_valuations while keeping read-only tools active.

Every tool invocation, such as running list_investors, is logged directly to your OpenAI developer dashboard. You can inspect the exact tool inputs, outputs, and model reasoning steps in real-time.

Yes, the SDK can trigger multiple tools concurrently, such as pulling get_company and list_filings at the same time. This speeds up your investment research pipelines.

All LP lists, fund performance metrics, and portfolio valuations are processed inside isolated V8 sandboxes. Vinkius handles the underlying authorization, meaning your raw credentials never touch the OpenAI LLM or external logs.

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