Detect Product-Market Fit Signals Using MCP.
Tech stack analyzed, company growth verified, traction signals scored , verify product-market fit from the outside before you write the check
Works with every AI agent you already use
…and any MCP-compatible client
Waiting for input…
Gemini How It Works
Here is what the tech stack tells you that the pitch deck never will. Your AI agent queries BuiltWith for the startup's domain , acmepayments.com.
BuiltWith returns the full technology fingerprint: Frontend: React, Next.js (modern stack , good). Hosting: AWS (standard). Analytics: Segment, Mixpanel, Google Analytics (triple-layered analytics means they are measuring everything , PMF-seeking behavior).
Payments: Stripe, Stripe Billing (they are charging customers , revenue exists). Support: Intercom (they have enough users to need support tooling).
CRM: HubSpot (they have a sales process). Marketing: Customer.io, Google Ads (they are spending on acquisition). Error tracking: Sentry (they care about production reliability).
That tech stack tells a story: this is a company that is charging customers, measuring usage, supporting users, running a sales process, and investing in acquisition.
That is operational maturity consistent with early PMF. Now compare that to the second Seed company you are evaluating , CompetitorX.com: Hosting: Vercel.
Analytics: Google Analytics only. Payments: none detected. Support: none. CRM: none. That is a landing page, not a product. Clearbit adds the quantitative layer: Acme has 42 employees (up from 28 six months ago).
Estimated revenue: $4-6M. CompetitorX has 8 employees and no revenue signal. The agent builds a Google Sheets PMF scorecard: 12 signals measured, scored 0-3, composite PMF confidence score.
Acme scores 31/36 (high PMF evidence). CompetitorX scores 8/36 (pre-PMF). You know which check to write.
MCP Server Orchestration: 3 MCP Servers, one intelligent agent
Connect BuiltWith, Clearbit and Google Sheets MCP servers so your AI agent analyzes a startup's technology stack through BuiltWith (what tools they use, what analytics they run, what payment systems they integrated), enriches the company profile through Clearbit (employee count, estimated revenue, growth trajectory), and compiles a product-market fit evidence report in Google Sheets. Every Seed founder says 'We have strong product-market fit.' But PMF is not a feeling , it is a set of observable signals. A company running Stripe billing + Segment analytics + Intercom support + HubSpot CRM is operationally mature. A company with only a landing page and Google Analytics is still pre-product. Your agent reads the signals the founder cannot hide.
Builtwith Tech Lookup
triggerAnalyzes the startup's technology stack, analytics, payments and infrastructure
lookup_domain_tech get_domain_company_info get_domain_trust get_domain_keywords Clearbit Hubspot
actionEnriches company profile , employee count, revenue estimate, growth signals
find_company find_person_and_company autocomplete_company find_risk Google Sheets
actionCompiles the PMF evidence report with scoring
create_spreadsheet append_sheet_values update_sheet_values get_spreadsheet Run This Automation Today
Connect Claude, ChatGPT, Cursor, or any AI agent to the Vinkius catalog and run this automation in minutes.
Build Your Own MCP
Turn any internal API into an MCP server. 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
Connect & Automate
The 3 servers this recipe uses are ready in the catalog. Connect them once, paste a prompt, and your AI runs the full workflow.
- Builtwith Tech Lookup, Clearbit Hubspot & Google Sheets ready in the catalog right now
- Add more from 4,700+ servers whenever you need
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers and recipes added every week
Superpowers you didn't know your AI had
The Vinkius catalog gives your agent access to 4,700+ MCP servers and the intelligence to combine them. Imagine never logging into another dashboard. Your AI handles the work across every tool, in one conversation. That's what this infrastructure was built for.
Cross-Platform Intelligence
Your agent doesn't just connect to tools. It understands the relationships between them. Data flows where it needs to go, automatically, with full context preserved across every platform.
Contextual Reasoning
Every decision your agent makes considers the full picture. It reads CRM data, checks calendars, reviews conversation history, and acts on everything at once. Not step by step. All at once.
Productivity at Scale
What used to take 45 minutes across five different dashboards now takes one sentence. Your agent runs the entire workflow end to end while you focus on decisions that actually matter.
Zero-Config Reliability
No API keys to paste. No webhooks to configure. No YAML to debug. Connect your MCP servers once, and your agent handles the rest. Every time, without intervention.
Made for
exactly this
Your AI agent taps into the entire Vinkius MCP catalog to handle these for you. You describe what you need. It does the rest.
Seed-stage VCs performing pre-meeting diligence who want to verify product-market fit claims before scheduling a partner call with the founder
Angel investors evaluating 10+ deals per month who need a rapid, data-driven way to separate companies with real traction from companies with just a pitch deck
VC associates building deal screening reports who need external signals to supplement the founder's self-reported metrics
Accelerator selection committees reviewing applications who need a scalable method to verify which applicants have shipped a real product versus a prototype
Frequently Asked Questions About This MCP Server Orchestration
Which MCP servers do I need for this workflow?
Three: BuiltWith, Clearbit and Google Sheets. Connect all three to your AI client before running any prompt from this page.
Does this work with Claude Desktop, Cursor or Windsurf?
Yes. Any AI client that supports the Model Context Protocol works , Claude Desktop, Cursor, Windsurf, Cline and others. Connect the MCP servers and paste a prompt.
Can a startup hide their tech stack?
Partially. Some technologies are visible in the page source (JavaScript libraries, analytics scripts, payment embeds). Server-side technologies are harder to detect. BuiltWith catches what is client-visible , which covers most SaaS tooling. A startup that actively hides their tech stack is unusual and worth asking about.
Is the PMF score reliable?
The score measures observable operational signals , not product-market fit directly. A high score means the company has built infrastructure consistent with having paying customers and a real product. It is a proxy, not a guarantee. Use it to prioritize due diligence, not to replace it.
Can I customize the scoring criteria?
Yes. Tell the agent your priorities. If you weight payment integration 5x over analytics, the scoring adjusts. The framework is flexible , your investment thesis determines the weights.
Does this work for B2B and B2C startups?
Yes, but the signals differ. B2B startups show CRM, billing, and support tools. B2C startups show analytics, ad platforms, and engagement tools. Adjust your scoring criteria based on the business model.
Run Technical Due Diligence Using MCP Servers
Funding data pulled, tech stack analyzed, diligence report built , evaluate startup infrastructure without asking for a demo
Screen Accelerator Applications Using MCP
10,000 applications received, companies verified, fake traction filtered , shortlist the real startups from the noise in hours, not weeks
Spot Competing Startups Using MCP Servers
Tech stacks compared, market overlap mapped, duplicate startups flagged , catch two batch companies building the same product before Demo Day embarrasses everyone
MCP Servers for Investment Committee Memos
Company enriched, funding history pulled, IC memo structured , your investment committee prep goes from 8 hours to 30 minutes
MCP Servers to Match Founders With Peer Networks
Cohort companies profiled, mutual-benefit pairs identified, peer introductions sent , activate the most powerful part of your program: founders helping founders
Benchmark Seed Valuations Using MCP Servers
Your portfolio valuations compared, market comps pulled, benchmark report built , know if $12M pre-money for a Seed is reasonable before you negotiate
MCP servers used in this workflow
BuiltWith Tech Lookup
BuiltWith Tech Lookup MCP Server gives you immediate visibility into any website's technology stack. Run the `lookup_domain_tech` tool to detect the CMS, analytics, hosting, and frameworks used by millions of domains. Use it for competitive research, lead qualification, or auditing digital infrastructure.
Clearbit (HubSpot)
Clearbit (HubSpot) MCP Server connects your B2B intelligence directly into your AI agent. Use it to enrich person and company data by email address or domain name. You can audit leads, find company firmographics (industry, size), discover new prospects by tech stack, or calculate risk scores without leaving your chat interface.
Google Sheets
Google Sheets MCP Server lets your AI client read, write, and manage data directly in Google Sheets. Use conversational commands to pull data from specific ranges, append new rows, or structure entire spreadsheets. It acts as an analyst, letting you manipulate complex data without opening the GUI or writing formulas.