How to Use the DecileHub MCP in AutoGen

Q: How do I load DecileHub MCP Server tools into AutoGen?

Install autogen-extmcp. Pass your endpoint to mcpservertools using StreamableHttpServerParams. The framework handles the schema translation so you can drop the tools straight into your AssistantAgent.

Give your AutoGen multi-agent teams direct access to DecileHub portfolio and valuation metrics.

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 AutoGen

Create your Vinkius account to connect DecileHub 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 DecileHub with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Equip AutoGen agents with data

This MCP Server feeds hard financial data directly into your AutoGen agent debates. You can assign these tools to a specific analyst agent. While the risk agent argues for caution, the analyst agent pulls hard numbers using `get_fund_performance` to back up its position. The debate shifts from hypotheticals to concrete metrics. If the team needs to evaluate a specific asset, they trigger `get_company` and `list_valuations`. They negotiate the asset's true worth based on the returned data.

Cross-check investor profiles

Run consensus-driven due diligence by giving your agents access to this server. One agent can run `list_investors` to gather the LP base, while a compliance agent reviews their background. They pass the IDs back and forth, calling `get_investor` for deep dives. You get a consensus-driven output. The agents challenge each other's interpretations of the data. They verify system connectivity with the MCP endpoint using `check_decilehub_status` before finalizing their joint report.

Analyze regulatory filings

Analyze complex regulatory filings by letting your agents query this server. A legal agent pulls the raw text via `get_filing_report`. A financial agent reads the same text and highlights different risks. They argue over the implications until they reach an agreement. You just watch the logs as they work. The system handles the back-and-forth automatically. They use `list_filings` to ensure they did not miss any recent amendments before signing off.

Setup guide

Set up DecileHub 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 DecileHub 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="DecileHub_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent DecileHub 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 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 AutoGen

Install `autogen-ext[mcp]`. Pass your endpoint to `mcp_server_tools` using `StreamableHttpServerParams`. The framework handles the schema translation so you can drop the tools straight into your `AssistantAgent`.

You configure which agents get tool access. Usually, you give the tools to a dedicated data-gatherer agent, who then shares the retrieved portfolio metrics with the rest of the chat group.

Yes. The server supports standard streamable HTTP connections. This keeps the connection alive while your agents debate the outputs of tools like `list_funds`.

That is the whole point of the framework. They will continue prompting each other and might even execute `list_companies_by_fund` again with different parameters to resolve the dispute.

Vinkius isolates every session. When your agents pull sensitive LP names or commitment amounts, the data lives only in that specific execution context. Once the chat terminates, the sandbox is destroyed completely.

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