Founder Vision Prover MCP. Audit your startup against real financial viability.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Founder Vision Prover forces your AI client to audit a startup idea like a ruthless VC partner. Instead of vague 'large market' claims, it requires proof across five axes: behavioral pain evidence, bottom-up TAM calculation, M3 cohort retention data, structural zero-CAC distribution loops, and unit economics modeling that guarantees capital payback under 12 months.
What your AI agents can do
Validate founder vision
Runs a structured audit against five mandatory business metrics: behavioral evidence, bottom-up market sizing, retention physics, structural distribution loops, and unit economics.
The tool forces calculation of Total Addressable Market by multiplying a specific number of reachable customers by their annual contract value.
It requires evidence that the target customer is currently using an expensive or painful workaround to solve the problem, proving immediate willingness to pay.
The tool analyzes specific cohort data (Month 3) against industry standards for both consumer and enterprise SaaS models.
It determines if the business model relies on structural growth mechanisms—like network effects or product-led virality—rather than paid advertising.
The tool calculates customer acquisition cost (CAC) payback periods and pinpoints the exact month when revenue exceeds operational burn rate.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Founder Vision Prover MCP Server: 1 Tool for Deep Auditing
Use the validate_founder_vision tool to audit any startup idea against five mandatory metrics required by top-tier venture capital firms.
019e6512validate founder vision
Runs a structured audit against five mandatory business metrics: behavioral evidence, bottom-up market sizing, retention physics, structural distribution loops, and unit economics.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Founder Vision Prover, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
Look, when you're pitching an idea, you don't need buzzwords; you need math. The Founder Vision Prover doesn't give you platitudes about a 'large market.' It forces your AI client to run a brutal audit against five non-negotiable business metrics using the validate_founder_vision tool.
It starts by demanding proof of actual customer pain points through Auditing Behavioral Pain Points. This isn't some vague description; it requires evidence that the target user is already spending money or wasting time on a costly, painful workaround today. That proves immediate willingness to pay, plain and simple.
Next, you gotta prove the market size correctly. The tool calculates Bottom-Up TAM by making you multiply two specific numbers: the total number of reachable customers * their annual contract value. You can't just cite a big report from some think tank; you gotta show the hard math that backs it up.
Retention is next. To check your viability, it runs Modeling Cohort Retention Rates. This tool analyzes deep-dive cohort data—specifically looking at Month 3 retention numbers—and checks them against industry benchmarks for both consumer products and enterprise SaaS models. Signups are vanity metrics; true retention physics is the only thing that matters.
The model then determines your structural advantage by Identifying Structural Moats. It won't let you claim growth just because you plan to run ads. Instead, it verifies if your business relies on inherent mechanisms like network effects or product-led virality—the kind of free, structural loop that makes competitors irrelevant.
Finally, the tool hits unit economics hard by Determining Unit Economics Viability. It calculates your Customer Acquisition Cost (CAC) payback period and pinpoints the exact month where revenue finally surpasses your operational burn rate. You'll know precisely when you cross the line from spending money to actually making it.
The validate_founder_vision tool binds all these checks together, running a structured audit that forces five specific decision pivots before declaring any idea viable. It combines Behavioral Evidence, Bottom-Up Market Sizing, Retention Physics, Structural Distribution Loops, and detailed Unit Economics into one comprehensive report. You run the validate_founder_vision tool to calculate your Bottom-Up TAM, audit behavioral pain points proving immediate willingness to pay, model cohort retention rates against industry standards, identify structural moats like network effects, and determine unit economics viability by calculating CAC payback periods.
How Founder Vision Prover MCP Works
- 1 Feed your startup idea, target market details, and preliminary financial assumptions into the
validate_founder_visiontool. - 2 The agent processes the data, running mandatory checks against five decision pivots: behavioral proof, bottom-up sizing, retention physics, distribution moat structure, and unit economics.
- 3 You receive a detailed verdict that flags any specific violation (e.g., TOP_DOWN_DELUSION or BEHAVIORAL_VOID) and names the exact startup assumption failure.
The bottom line is: It strips away marketing fluff, forcing your idea to pass rigorous, data-driven financial and behavioral tests before it’s considered viable.
Who Is Founder Vision Prover MCP For?
Founders who can't tell the difference between a good pitch deck and a real business model. Product Managers who are tired of building features nobody will pay for. Strategy consultants who need to stop advising clients on 'large markets' and start talking about unit economics.
Uses it to force themselves (and their team) to confront the five failure points in a business plan, moving beyond optimistic guesswork.
Runs preliminary checks on new product ideas before committing engineering resources, ensuring the market pain is immediate and quantifiable.
Validates incoming pitches by systematically checking for structural flaws like reliance on top-down TAM or weak distribution moats.
What Changes When You Connect
- Stops you from relying on vague 'large market' claims. It forces the calculation of Total Addressable Market using a bottom-up, customer count model instead of Gartner reports.
- It proves if the pain is acute enough to pay for. The tool demands present-tense behavioral evidence—what the user hacks today—not just how frustrated they feel.
- You finally understand retention. Instead of looking at signups, the Prover focuses on M3 cohort data, telling you if your product actually sticks with users.
- It makes distribution structural. You learn if your growth loop is based on virality or network effects, rejecting simple paid ad models that scale linearly and cost more.
- You define cash flow timing. The tool calculates CAC payback period, ensuring the business recovers its acquisition costs in under 12 months—no zombie economics.
Real-World Use Cases
Pitching to VCs
A founder wants funding for a SaaS platform. They run validate_founder_vision. The tool flags that their TAM is too big and unproven, forcing them to narrow the focus to a specific niche market (a 'wedge') with verifiable customer counts under $100M.
Revising Product Strategy
A PM has a new idea but only shows 50k downloads. Running validate_founder_vision forces the model to reject these vanity metrics, demanding M3 cohort retention data instead so they know if users stick around after the initial novelty wears off.
Fixing Weak Business Models
A team thinks their paid advertising budget is enough for growth. The tool identifies this as 'Distribution Naivety,' forcing them to pivot and instead build a structural loop, like requiring users to invite suppliers (network effect) to drive CAC toward zero.
Pre-mortem Planning
Before launch, the team uses the tool to stress test their unit economics. If the payback period is calculated as 18 months, they know immediately that they need significantly more capital runway than planned, preventing a cash crisis.
The Tradeoffs
Using Top-Down Market Sizing
Stating the market is '$50 Billion according to Gartner.' This approach guarantees nothing because it counts potential users, not reachable ones.
→
Always use validate_founder_vision and calculate TAM as [N actual customers] × [Your price]. Stick to bottom-up math.
Focusing on Downloads/Waitlists
Showing 50,000 downloads proves only interest, not product stickiness. The model will reject this as a 'Behavioral Void' metric.
→ Use the tool to demand M3 cohort retention data. Retention is the real measure of success.
Assuming Paid Ads are Growth
Planning growth solely through Google or Facebook ads treats acquisition as a scalable solution, ignoring increasing costs and competition.
→
Let validate_founder_vision check for structural moats. Focus on product-led growth or network effects to drive CAC toward $0.
When It Fits, When It Doesn't
Use this tool if you are past the 'idea' stage and are in a deep audit phase. You need hard numbers proving market size, retention physics, and unit economics—not just enthusiasm. Don't use it for initial brainstorming; that’s too early. If your only input is a vague promise like 'it will be huge,' this tool will reject you, and you should refine the pain point first. It's designed to catch fatal flaws (BEHAVIORAL_VOID, TOP_DOWN_DELUSION). Don't use it if you just need general advice; it requires specific inputs: customer hack examples, verifiable pricing models, and cohort data.
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 1 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
The headache today is relying on gut feeling instead of numbers.
Most founders start by creating a deck that uses big, round market numbers. They point to 'the global X industry'—a massive number—and assume they can capture 1%. This process feels good and looks impressive in a boardroom, but it’s meaningless because it doesn't tell you how many people are actually paying right now.
With the Founder Vision Prover, your AI client forces the math. It demands that you calculate TAM using only reachable customers multiplied by price. You get a single, verifiable number that shows if your market is big enough to matter and small enough to conquer.
Founder Vision Prover: Prove your idea's full viability.
Manual validation usually stops at 'Do people need this?' It ignores the financial gravity of running a business. You manually calculate TAM, but you forget to model month-over-month churn, or if the cost of acquiring one user will bankrupt you before you reach profitability.
This MCP Server handles all five physics simultaneously. It doesn't just say 'good idea'; it says whether your startup is mathematically viable by proving retention, a structural moat, and positive cash flow within 12 months.
Common Questions About Founder Vision Prover MCP
How does the Founder Vision Prover handle vague market claims? +
It rejects them automatically. The tool requires bottom-up math: you must show [Number of customers] multiplied by [Annual contract value]. General statements are flagged as TOP_DOWN_DELUSION.
Is the Founder Vision Prover useful if I don't have cohort data? +
No. The tool explicitly requires Month 3 cohort retention and will reject your pitch, flagging it for RETENTION_DEATH until you provide specific user stickiness metrics.
What is the difference between this Prover and a normal AI critique? +
A regular AI gives advice; the Founder Vision Prover performs an audit. It's designed to check for five specific, hard-coded physics violations—like ZOMBIE_ECONOMICS or BEHAVIORAL_VOID.
Can I use validate_founder_vision if my product is B2B? +
Yes. It adjusts the retention and TAM calculations for enterprise models, requiring high gross margins (above 80%) and defined annual contract values.
If `validate_founder_vision` identifies a flaw, what does the resulting Verdict Matrix mean? +
The matrix names the exact startup physics violation. Each failure pivot maps directly to a specific fatal flaw—like BEHAVIORAL_VOID if the customer isn't hacking a solution today. This tells you precisely where your business model breaks.
What AI clients can use the `validate_founder_vision` tool? +
It connects to any compatible AI client that supports Model Context Protocol (MCP). You simply need to configure your agent with MCP access via Vinkius. It’s designed for broad compatibility, not specific platforms.
Does `validate_founder_vision` require specific financial data formats? +
Yes, it requires structured metrics for accurate calculations. You must provide clear numbers: CAC, Annual Contract Value (ACV), and M3 cohort retention percentages. Fuzzy descriptions won't pass the checks.
Are there usage limits or rate caps when running `validate_founder_vision`? +
Usage is governed by your Vinkius subscription tier. We manage capacity to ensure reliable performance, but you should always check your dashboard for real-time rate limit details.
Does it predict if my startup will succeed? +
No. It validates STARTUP PHYSICS — the structural mechanics that make venture-scale growth possible. If your cohort retention leaks, your CAC payback is too slow, or your distribution is paid ads, no amount of vision will save the business. This tool stops the AI from flattering your bad ideas.
Why does it reject 'downloads' and 'signups' as proof of retention? +
Downloads, signups, and waitlist size are vanity metrics. They measure interest, not retention. The only metric that proves retention is COHORT data: of users who joined in Month 1, what percentage are STILL ACTIVE in Month 3? If you cannot answer that, you have a leaky bucket.
What is a 'Behavioral Hack'? +
If a problem is truly painful, the customer is already solving it TODAY using a hack — spreadsheets, interns, duct tape, custom scripts. They are spending money or time on an absurd workaround. If they are NOT hacking a solution, the pain is not real enough to justify a purchase.
Multi-server workflows that include Founder Vision Prover MCP
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Steve Jobs Vision Prover
A product had settings menus with 47 options and 15 integrations. This tool forces it to kill features, absorb complexity, and own the whole experience.
X Ads (Twitter)
Manage your X Ads campaigns — audit accounts, line items, and analytics via AI.
Anthropic Alternative
Access Claude models via Anthropic API — send messages, count tokens, manage batches and discover models from any AI agent.
You might also like
Copernicus Perspective Prover
Your AI analyzed the problem from the default perspective and added workarounds when it did not fit. That is an epicycle — not a solution. Copernicus did not add more epicycles to Ptolemy's model. He moved the center from Earth to Sun. 40+ epicycles vanished. This tool forces default questioning, epicycle counting, alternative framing, observer shifting, and simplicity comparison.
Techstars Mentor Prover
A founder pitched for 45 minutes without mentioning a single customer conversation, a single mentor challenge, or a single dollar of revenue. Zero feedback sought. Zero market validation. Zero network. That is not acceleration — that is solo building in a vacuum. This tool forces five Techstars-level axes: mentor leverage, feedback discipline, customer discovery, revenue readiness, and network strategy.
Workflow Orchestrator Prover
AI agents build fragile pipelines that fail silently, ignore rate limits, and double-process events. This prover enforces distributed systems discipline: mandatory dead-letter queues (DLQ), exponential backoff, stateful idempotency tracking, and secure credentials.
