How to Use the DeckMatch MCP in LangChain

Q: Can I trace DeckMatch tool latency in LangSmith?

Yes, every call to generateinvestmentmemo or searchstartupssemantically shows up as an individual tool execution step in your LangSmith dashboard. You can monitor input payloads, output variables, and execution times for every pitch deck processed.

Q: How does the DeckMatch MCP Server handle rate limits during batch processing in LangChain?

Check the connectivity status using getapistatus before starting your run. If you hit limits while calling listsubmissions across hundreds of startups, LangChain's built-in retry configurations will manage the backoff.

Q: How do I categorize incoming startups dynamically?

Use listsubmissiontags to fetch your active taxonomy, then let your LangChain agent decide which labels apply. The agent then calls tagsubmission to write those tags back to the deck record.

Feed startup decks directly to your LangChain agents to generate custom memos and track audit trails instantly.

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 LangChain

Create your Vinkius account to connect DeckMatch to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build automated investment chains in LangChain

The `submit_pitch_deck` tool sends incoming startups straight into your LangChain pipeline, initiating a multi-stage evaluation. Your agent takes the response and instantly feeds it into `get_deck_analysis` to pull critical metrics without manual intervention. Once analyzed, the chain triggers `generate_investment_memo` to compile findings for your team. Every step is tracked in LangSmith, giving you a clear view of how your agent moves from a raw PDF to a structured memo.

Semantic startup matching via MCP Server tools

Your agent uses `search_startups_semantically` to compare incoming decks against your historical portfolio database in LangChain. It queries similar business models to avoid funding direct competitors. If a match is found, the agent runs `get_submission_details` to pull the historical record and update the pipeline. This setup turns raw pitch data into structured context within your custom LangGraph chains.

Tag and audit pitch decks inside LangChain agents

The `tag_submission` tool applies custom categorization to every processed deck within your LangChain agent execution loop. This lets you organize your deal flow by industry or round size dynamically. To keep your compliance team happy, the agent calls `get_submission_audit` to verify who accessed or modified the deck data. You get a clean, auditable log of every single automated investment decision.

Setup guide

Set up DeckMatch MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes DeckMatch tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "deckmatch-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent DeckMatch transactions"
    })
    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 LangChain

Register the MCP Server using MultiServerMCPClient and pass the tools to your LangGraph agent. Your agent can then call `submit_pitch_deck` and pass the resulting ID directly to `get_deck_analysis` in a single execution loop.

Yes, every call to `generate_investment_memo` or `search_startups_semantically` shows up as an individual tool execution step in your LangSmith dashboard. You can monitor input payloads, output variables, and execution times for every pitch deck processed.

Check the connectivity status using `get_api_status` before starting your run. If you hit limits while calling `list_submissions` across hundreds of startups, LangChain's built-in retry configurations will manage the backoff.

Use `list_submission_tags` to fetch your active taxonomy, then let your LangChain agent decide which labels apply. The agent then calls `tag_submission` to write those tags back to the deck record.

Your raw pitch decks and generated investment memos are processed through secure sandboxed isolates on Vinkius. The server only transmits the minimum payload required for analysis, and you can permanently purge files at any time using `delete_submission`.

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