How to Use the DeckMatch MCP in LlamaIndex

Q: Can I perform semantic search across my decks using DeckMatch and LlamaIndex?

Yes, your LlamaIndex agent can call searchstartupssemantically to find similar business models in your pipeline. This bypasses traditional keyword search by looking at the actual concepts inside the pitch decks.

Q: How does the DeckMatch MCP Server handle document chunking for long pitch decks?

The server handles the heavy lifting when you run submitpitchdeck. It extracts the key metrics and text, presenting clean, structured metadata that LlamaIndex can index without complex pre-processing.

Q: How do I filter my queries by specific startup sectors?

Run listsubmissiontags to see your available categories, then apply those tags to your LlamaIndex metadata filters. You can then query only the submissions that have been labeled via tagsubmission.

Index pitch deck analyses directly into your LlamaIndex vector stores for semantic retrieval.

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 LlamaIndex

Create your Vinkius account to connect DeckMatch to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index startup pitch analyses in LlamaIndex

The `get_deck_analysis` tool fetches structured evaluation data that LlamaIndex ingests directly into your document indexes. This prevents your agent from hallucinating startup metrics during partner meetings. By feeding the output of `get_submission_details` into your index, you build a searchable knowledge base of active deals. Your queries retrieve factual, real-time data instead of stale spreadsheet exports.

Query similar startups using the DeckMatch MCP Server

The `search_startups_semantically` tool queries your active deal flow to find direct competitors or similar business models. LlamaIndex uses this tool to ground its retrieval pipeline in actual market data. Your agent combines these search results with external vector databases to evaluate market saturation. It maps the competitive landscape using real data from `list_submissions` instead of guessing.

Generate and index investment memos automatically

The `generate_investment_memo` tool creates structured investment briefs based on analyzed pitch decks. LlamaIndex indexes these memos as fresh document nodes, making them instantly queryable by your team. If you need to verify the source of a memo's claims, your agent can call `get_submission_audit` to trace the data back to the original deck. This keeps your investment thesis grounded in verified submission data.

Setup guide

Set up DeckMatch MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all DeckMatch MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to DeckMatch tools.",
)
response = await agent.run("List recent DeckMatch data")

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 LlamaIndex

Initialize the BasicMCPClient and convert the MCP tools using McpToolSpec. Your agent can then pull data via `get_deck_analysis` and insert the resulting text nodes directly into a VectorStoreIndex.

Yes, your LlamaIndex agent can call `search_startups_semantically` to find similar business models in your pipeline. This bypasses traditional keyword search by looking at the actual concepts inside the pitch decks.

The server handles the heavy lifting when you run `submit_pitch_deck`. It extracts the key metrics and text, presenting clean, structured metadata that LlamaIndex can index without complex pre-processing.

Run `list_submission_tags` to see your available categories, then apply those tags to your LlamaIndex metadata filters. You can then query only the submissions that have been labeled via `tag_submission`.

All startup pitch decks and evaluation metrics are isolated within Vinkius's zero-trust MCP runtime. Your LlamaIndex pipeline communicates over encrypted channels, and you can instantly wipe any record 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