How to Use the YC Startup Prover MCP in CrewAI

Assemble a team of autonomous startup critics using CrewAI and the YC Startup Prover.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect YC Startup Prover MCP to CrewAI

Create your Vinkius account to connect YC Startup Prover to CrewAI — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup YC Startup Prover with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

CrewAI squads powered by the YC Startup Prover MCP Server

One agent can't properly audit an entire business plan. You set up a CrewAI team where a research agent extracts the claims, an analyst agent runs the `validate_yc_startup` tool, and a moderator agent delivers the final verdict. This setup mimics a real venture capital investment committee. The analyst agent applies Paul Graham's strict criteria to the extracted data. It aggressively looks for solution-seeking behavior, demanding proof that the founder actually talked to users instead of just building a proprietary algorithm in a vacuum.

Deploy autonomous traction monitors

Celebrating signups is a trap. You assign a specific agent to strip away vanity metrics like Instagram followers and focus purely on default alive calculations. This specialized worker refuses to pass the pitch forward until it finds concrete monthly recurring revenue numbers. Shared memory allows the crew to cross-reference the financial data with the stated user acquisition strategy. If the marketing agent spots premature scaling like renting a commercial kitchen for a tiny early customer base, it alerts the rest of the team to reject the application.

Enforce manual onboarding rules

Ivory tower development kills brilliant technical teams. The autonomous squad checks the weekly user conversation logs to see what surprised the founder and what changed because of that feedback. Pitches lacking specific names and current workarounds fail the review. Sequential execution guarantees the problem gets validated before the technology even gets discussed. The final output forces the entrepreneur to define the one thing they do ten times better than the alternative, cutting through all feature bloat.

Setup guide

Set up YC Startup Prover MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke YC Startup Prover tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="YC Startup Prover Analyst",
    goal="Access and analyze YC Startup Prover data via MCP.",
    backstory="Expert analyst with direct YC Startup Prover access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent YC Startup Prover transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="YC Startup Prover Analyst",
        goal="Access and analyze YC Startup Prover data via MCP.",
        backstory="Expert analyst with direct YC Startup Prover access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent YC Startup Prover transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 YC Startup 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 YC Startup 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 YC Startup Prover MCP in CrewAI

Pass the endpoint URL directly into the mcps array in your agent definition. The framework handles the HTTP transport and exposes the startup evaluation logic to that specific worker.

You should assign the validation logic to a specialized analyst agent. Other members of the crew can gather the pitch data and pass it to the analyst through shared memory for a final verdict.

The evaluation rejects page views and free downloads entirely. Your agent will only approve pitches that demonstrate strong weekly retention curves and actual willingness to pay.

The tool flags any business plan lacking weekly customer conversations. Your crew will demand evidence of manual, unscalable actions before accepting any automated growth strategies.

Customer interview transcripts and capitalization tables remain strictly confidential. The zero-trust MCP architecture processes your startup data in a temporary isolate that self-destructs the moment the agent finishes its critique.

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