How to Use the DeckMatch MCP in AutoGen

Q: How do my AutoGen agents access DeckMatch tools?

Load the tools using mcpservertools with your Vinkius HTTP endpoint. Pass the resulting tool list to your AssistantAgent constructor so they can collaboratively call functions like submitpitchdeck using the MCP integration.

Q: Can multiple AutoGen agents use DeckMatch tools simultaneously?

Yes, one agent can run searchstartupssemantically to find competitors while another calls getdeckanalysis. The AutoGen framework coordinates their conversations and tool executions without collisions.

Q: How do agents handle conflicting data from a pitch deck?

Your agents can call listenrichmentsources to verify where the data came from. If a conflict arises during debate, they can query the raw audit trail via getsubmissionaudit to resolve the discrepancy.

Let your AutoGen agents debate startup viability and draft investment memos collaboratively.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeckMatch MCP to AutoGen

Create your Vinkius account to connect DeckMatch 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 DeckMatch with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent pitch evaluation with DeckMatch

The `submit_pitch_deck` tool kicks off a multi-agent debate by feeding a new startup into your AutoGen group chat. An analyst agent runs `get_deck_analysis` while a finance agent scrutinizes the numbers. They debate the startup's viability in real time, challenging each other's interpretations of the metrics. This collaborative process ensures your investment decisions are thoroughly vetted before you write a check.

Draft memos using this specialized MCP Server

The `generate_investment_memo` tool lets your AutoGen writer agent draft a comprehensive investment thesis. Meanwhile, a compliance agent runs `get_submission_audit` to verify the data sources. The agents negotiate the final language of the memo, correcting errors and adding context before saving. This workflow replaces manual drafting with a rigorous, multi-agent editorial process.

Automated pipeline tagging in AutoGen

The `tag_submission` tool allows your triage agents to categorize startups based on group consensus. One agent proposes a sector tag, and another verifies it against `list_submission_tags` before applying it. If the agents decide a startup doesn't fit your investment thesis, they can trigger `delete_submission` to keep your pipeline clean. Every tag and status change is negotiated and recorded automatically.

Setup guide

Set up DeckMatch 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 DeckMatch 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="DeckMatch_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Load the tools using mcp_server_tools with your Vinkius HTTP endpoint. Pass the resulting tool list to your AssistantAgent constructor so they can collaboratively call functions like `submit_pitch_deck` using the MCP integration.

Yes, one agent can run `search_startups_semantically` to find competitors while another calls `get_deck_analysis`. The AutoGen framework coordinates their conversations and tool executions without collisions.

You can restrict which agents have access to destructive tools like `delete_submission`. Only assign the admin agent the rights to remove data, while analyst agents are limited to read-only tools like `get_submission_details`.

Your agents can call `list_enrichment_sources` to verify where the data came from. If a conflict arises during debate, they can query the raw audit trail via `get_submission_audit` to resolve the discrepancy.

Yes, Vinkius runs the MCP Server in an ephemeral sandbox, meaning your custom investment memos and pitch analysis data are never stored permanently on the host. You control the lifecycle of all submission records.

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