How to Use the Founder Vision Prover MCP in Google ADK

Q: Can I restrict which tools the Google ADK agent can access?

Yes, you can use the toolnames filter when setting up the toolset. This ensures your agent only exposes the validation tool to keep the model focused on startup validation.

Run brutal YC-style diligence on BigQuery data with Google ADK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Founder Vision Prover MCP to Google ADK

Create your Vinkius account to connect Founder Vision Prover to Google ADK 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 Founder Vision Prover with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate customer workarounds directly from BigQuery

The `validate_founder_vision` tool connects directly to your Gemini-powered pipelines to analyze raw qualitative research. Instead of accepting generic claims of user interest, the tool scans for concrete workarounds where users spend real money on manual hacks. By feeding this tool data directly from your warehouse, your Google ADK agent instantly flags pitches that lack behavioral proof. You save hours of manual reading by letting the model run these checks at scale.

Build bottom-up TAM models with Gemini long-context

This MCP Server uses the massive token limits of Gemini to parse entire data rooms. Your agent calls `validate_founder_vision` to calculate bottom-up TAM, ignoring useless analyst reports in favor of real contract math. The system forces a wedge-and-expand analysis if the initial target market falls below the $100 million threshold. This ensures your investment thesis relies on real numbers rather than slide-deck fluff.

Audit retention and unit economics using Google ADK

The `validate_founder_vision` tool acts as a financial gatekeeper in your evaluation pipeline. It checks that Month 3 cohort retention is above 80% for SaaS and that the customer acquisition cost payback period is under 12 months. If the unit economics fail these physics, your agent immediately halts the workflow. This keeps your pipeline focused on companies that actually recycle capital fast enough to scale.

Setup guide

Set up Founder Vision Prover MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Founder Vision Prover tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Founder Vision Prover_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Founder Vision Prover tools via MCP.",
    tools=mcp_tools,
)

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 Founder Vision Prover. 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 Founder Vision Prover 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 Founder Vision Prover MCP in Google ADK

Install the package and initialize the MCP server with the HTTP transport URL. Pass this toolset to your `LlmAgent` so your Gemini model can call the `validate_founder_vision` tool during document analysis.

Yes, you can run the tool across thousands of rows of startup data stored in BigQuery. The server handles concurrent requests efficiently, allowing your agent to run unit economic checks on entire portfolios.

Gemini will fail the run if the input data lacks verifiable bottom-up calculations or shows a payback period longer than 12 months. The tool enforces these metrics strictly at the schema level.

Yes, you can use the `tool_names` filter when setting up the toolset. This ensures your agent only exposes the validation tool to keep the model focused on startup validation.

Your cohort retention spreadsheets and unit economics data are processed entirely within a zero-trust, ephemeral sandbox. Vinkius handles the connection securely, ensuring your raw financial inputs are never logged or stored on external disks.

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