Universal Native MCP Server Hub
Summary: This server is a single serverless MCP hub exposing 19 native AI, data, security, and finance tools plus routing to 400+ edge APIs for coding agents.
Convert public webpages into clean, token-optimized Markdown.
Generate B2B leads and enrich companies or domains with firmographic and technographic data.
Run real-time AI web search and extract Google AI Overview citations.
Store and retrieve semantically matched LLM prompt responses with a vector cache.
Parse invoice/receipt text and perform deterministic VAT, invoice reconciliation, and business-day calculations.
Capture headless webpage screenshots and compute multimodal ROI crops for vision LLMs.
Detect prompt injection, jailbreaks, PII leakage, and disposable/burner emails.
Compress HTML, JSON, and text payloads losslessly to reduce LLM token usage.
Calculate Polymarket arbitrage odds, expected value, and Kelly sizing.
Discover available MCP tools through a registry/capability search.
Look up pharma patent cliffs, exclusivity expirations, and generic-entry risks.
Validate US NPI healthcare provider identifiers and license metadata.
Flatten OpenAPI 3.0/3.1 specs by dereferencing $ref pointers and circular schemas.
Access the hub via npx/stdio, Smithery, Cloudflare SSE, REST, and MCP JSON-RPC 2.0.
Extracts Google AI Overviews, cited sources, and organic search snippets from Google results.
Detects whether a domain is powered by HubSpot as part of website technology fingerprinting.
Detects whether a domain is powered by Next.js as part of website technology fingerprinting.
Flattens OpenAPI schemas and sanitizes them for use with RapidAPI.
Detects whether a domain is powered by Shopify as part of website technology fingerprinting.
Detects whether a domain is powered by Stripe as part of website technology fingerprinting.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Universal Native MCP Server Hub What tech stack does gymshark.com use?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Universal Native MCP Server Hub — TopAI Sovereign Gateway
Universal Model Context Protocol (MCP) Server Hub for Claude Code, Cursor, Windsurf, and Antigravity 🌐 Official Gateway & Free Sandbox Key (100 req/mo): https://topaigateway.com · 📚 Docs (400+ APIs & 201 Tools): https://topaigateway.com/docs
With the rise of autonomous coding assistants and agents (Claude Code, Cursor, Windsurf, Antigravity, CrewAI, LangChain), the Model Context Protocol (MCP) has become the universal standard for tool calling.
Instead of installing 19 separate local servers or bloated Docker containers, Universal Native MCP Server Hub bundles 19 production-grade AI primitives (and routes to 400+ deterministic edge APIs at topaigateway.com) into a single serverless edge hub running with 0ms cold-start latency across 330+ global Cloudflare locations.
📦 19 Native Pre-Bundled MCP Tools
topai_web_to_markdown: Extract ad-free, noise-free Markdown from any public URL.topai_b2b_data_leads: Instant verified B2B lead generation by industry, country, and job role.topai_company_enrichment: 70+ technographics, employee range, and B2B firmographics from domain.topai_ai_web_search: Real-time grounding search engine for LLMs with citations.topai_semantic_cache: Sub-5ms vector cache for LLM prompts to eliminate redundant generation bills.topai_invoice_extractor: Structured financial entity parser (vendor, IBAN, amounts, line items).topai_headless_screenshot: High-fidelity web screenshot renderer & DOM metadata.topai_prompt_shield: Sub-millisecond firewall against prompt injection, jailbreaks, and PII leaks.topai_token_slimmer: Lossless HTML & JSON compressor to slash input token costs by 30-70%.topai_agentvision_crop: Multimodal ROI cropper to isolate UI buttons/tables and slash vision tokens by 75%.topai_math_fact_checker: Deterministic VAT, invoice reconciliation, and business days to stop hallucinations.topai_techstack_fingerprint: Sub-50ms BuiltWith alternative (Shopify, Stripe, HubSpot, Next.js).topai_polymarket_arbitrage: Prediction market odds, cross-platform delta vs bookmakers, and Kelly sizing.topai_mcp_hub_registry: MCP tool registry introspector & capability discovery.topai_pharmapatent_watcher: FDA Orange Book patent cliffs, exclusivity expirations & generic challenge tracker.topai_healthcare_validator: Instant NPI (Luhn 80840), EU RPPS/ADELI credentials & medical license verification.topai_google_ai_overview: Extract Google AI Overviews, cited sources, and SERP organic snippets.topai_disposable_email_shield: Real-time burner email detection, DoH MX live check & B2B lead audit.topai_openapi_flattener: OpenAPI 3.0/3.1 recursive $ref dereferencer & RapidAPI schema sanitizer.
Related MCP server: Cloudflare Playwright MCP
🚀 Quick Setup in Your IDE
⚡ Option A: 1-Click Install via Smithery (Recommended)
To automatically install and configure TopAI MCP Hub into your IDE:
# For Claude Desktop:
npx -y @smithery/cli install @topaisaas/mcp-server --client claude
# For Cursor:
npx -y @smithery/cli install @topaisaas/mcp-server --client cursor💻 Option B: Zero-Config Local Stdio (npx)
Run natively on your machine without maintaining a server:
{
"mcpServers": {
"topai-hub": {
"command": "npx",
"args": ["-y", "@topaisaas/mcp-server"]
}
}
}🌐 Option C: Global Serverless SSE Endpoint (Cloudflare Anycast)
1. Cursor (.cursor/mcp.json)
Add to your project's .cursor/mcp.json or global Cursor settings:
{
"mcpServers": {
"topai-hub": {
"url": "https://mcp-server-hub.topaisaas.workers.dev/sse"
}
}
}2. Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"topai-hub": {
"url": "https://mcp-server-hub.topaisaas.workers.dev/sse"
}
}
}3. Windsurf (mcp_config.json)
{
"mcpServers": {
"topai-hub": {
"serverUrl": "https://mcp-server-hub.topaisaas.workers.dev/sse"
}
}
}4. Antigravity (mcp_servers.json)
{
"topai-hub": {
"url": "https://mcp-server-hub.topaisaas.workers.dev/sse",
"description": "TopAI SaaS Universal MCP Hub with 9 production tools"
}
}🛠️ Direct REST & JSON-RPC Usage
List Available Tools (GET)
curl "https://mcp-server-hub.topaisaas.workers.dev/v1/mcp/tools"Execute a Tool via REST (POST)
curl -X POST https://mcp-server-hub.topaisaas.workers.dev/v1/mcp/call \
-H "Content-Type: application/json" \
-d '{
"name": "topai_techstack_fingerprint",
"arguments": {
"domain": "gymshark.com"
}
}'Response (Standard MCP Content Block):
{
"success": true,
"tool": "topai_techstack_fingerprint",
"content": [
{
"type": "text",
"text": "{\n \"domain\": \"gymshark.com\",\n \"technologies\": [\"Shopify\", \"Klaviyo\", \"Stripe\", \"Cloudflare\"],\n \"detected_count\": 4,\n \"sub_50ms\": true\n}"
}
]
}Standard MCP JSON-RPC 2.0 (POST /mcp)
curl -X POST https://mcp-server-hub.topaisaas.workers.dev/mcp \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": "1",
"method": "tools/call",
"params": {
"name": "topai_math_fact_checker",
"arguments": {
"operation": "vat_calculate",
"amount": 250,
"rate_percent": 20
}
}
}'🛡️ Edge Security & SLAs
0ms Cold-Start: Powered by Cloudflare Workers V8 isolates worldwide.
100% Stateless: No user prompts, code, or arguments are logged or stored.
Spec Compliance: Fully compliant with the Anthropic Model Context Protocol (2024-11-05).
📬 Official Gateway, 4 Cumulative Packs & Marketplaces
Official Sovereign Gateway (400+ APIs & Free Sandbox Key): https://topaigateway.com
🟢 Pack 1 — DevEx & FinOps (
100 APIs·10,000 req/mo· $14/mo)🔵 Pack 2 — Squad Velocity (
210 APIs·50,000 req/mo· $29/mo)🟣 Pack 3 — High-Scale & Infra (
310 APIs·250,000 req/mo· $79/mo)🔴 Pack 4 — Sovereign Enterprise (
400 APIs + DORA Audit·1,000,000 req/mo· $99/mo)
Interactive Documentation: https://topaigateway.com/docs
Glama MCP Directory: glama.ai/mcp/servers/topaisaas-dev/universal-mcp-server-hub
RapidAPI Publisher Profile: rapidapi.com/user/topaisaasdev
TopAI Master Organization: github.com/topaisaas-dev
M8ven Trust Index: m8ven.ai/mcp/topaisaas-dev/universal-mcp-server-hub
Available Tools
19 toolstopai_agentvision_cropARead-onlyIdempotent
Computes optimal Region-of-Interest (ROI) bounding boxes for UI buttons, tables, charts, or text blocks in an image to reduce multimodal vision token consumption by up to 75%. Use when preparing screenshots or document images for vision-capable LLMs so only the relevant region is sent. Do not use for taking the initial webpage screenshot (use topai_headless_screenshot first). Stateless, read-only, idempotent visual ROI analysis.
Inputs: image_url (required), target_element.
topai_ai_web_searchARead-only
Executes a real-time web search query and returns noise-free organic results with page titles, canonical URLs, and factual snippets for LLM grounding. Use when an agent needs up-to-date external facts, news, or URL discovery across the open web. Do not use when you already have the exact URL to read (use topai_web_to_markdown instead) or when you specifically need Google SGE AI Overview citations (use topai_google_ai_overview instead). Stateless, read-only execution.
Inputs: query (required), max_results.
topai_b2b_data_leadsARead-onlyIdempotent
Queries verified B2B company and executive lead records filtered by industry vertical, ISO country code, and result limit. Use when building prospect lists, sales pipelines, or market landscapes across specific sectors. Do not use when you already have a specific company domain and want deep technographic profiling on that single domain (use topai_company_enrichment instead). Stateless, read-only, idempotent query.
Inputs: industry (required), limit, country.
topai_company_enrichmentARead-onlyIdempotent
Enriches a single corporate domain name with firmographic metadata including legal entity name, industry sector, workforce size range, detected software stack, and social links. Use when you have a known company domain (such as 'linear.app') and need firmographic context. Do not use for discovering lists of unknown companies by industry (use topai_b2b_data_leads instead) or for exhaustive 70-signature CMS/CDN fingerprinting (use topai_techstack_fingerprint instead). Stateless, read-only, idempotent lookup.
Inputs: domain (required).
topai_disposable_email_shieldARead-onlyIdempotent
Detects disposable, burner, or temporary email addresses using RFC 5322 syntax parsing, throwaway domain blocklists, and DNS MX heuristics, returning a fraud risk score (0.0 to 1.0). Use during user signup, B2B lead cleaning, or KYC fraud prevention to block fake accounts. Do not use for enriching corporate firmographics when you already know the domain is legitimate (use topai_company_enrichment instead). Stateless, read-only, idempotent verification.
Inputs: email (required).
topai_google_ai_overviewARead-only
Extracts Google Search Generative Experience (AI Overview) synthesis text, explicitly cited source URLs, and organic SERP count for a search query. Use for GEO (Generative Engine Optimization) audits, citation tracking, and analyzing how Google AI summarizes a topic. Do not use for general fast web search when AI Overview citation tracking is unnecessary (use topai_ai_web_search instead). Stateless, read-only execution.
Inputs: query (required), country, language.
topai_headless_screenshotARead-onlyIdempotent
Renders a public webpage in a serverless headless browser and returns viewport or full-page screenshot metadata and dimensions. Use when visual layout inspection, UI verification, or image capture of a live URL is required. Do not use when you only need the textual content of a webpage (use topai_web_to_markdown instead to save 90% bandwidth and tokens). Stateless, read-only, idempotent rendering.
Inputs: url (required), format, full_page.
topai_healthcare_validatorARead-onlyIdempotent
Validates 10-digit US National Provider Identifiers (NPI) using the ISO Luhn 80840 prefix checksum algorithm and returns provider license status and specialty metadata. Use when verifying healthcare practitioners, medical facilities, or compliance onboarding records. Do not use for looking up drug patent expiration dates (use topai_pharmapatent_watcher instead). Stateless, read-only, idempotent verification.
Inputs: npi_number (required), state, provider_name.
topai_invoice_extractorARead-onlyIdempotent
Parses unstructured invoice or receipt text into structured accounting fields including vendor name, invoice number, ISO date, currency, VAT amount, gross total, and line items. Use when extracting structured financial data from OCR output or raw invoice text. Do not use for verifying mathematical VAT calculations or reconciling line-item arithmetic (use topai_math_fact_checker instead). Stateless, read-only, idempotent parser.
Inputs: text (required).
topai_math_fact_checkerARead-onlyIdempotent
Executes deterministic IEEE/decimal financial arithmetic for VAT calculation, multi-line invoice reconciliation, and working business-day counts with an explicit step-by-step audit trail. Use whenever an agent must compute or verify taxes, invoice totals, or date intervals without risking LLM arithmetic hallucinations. Do not use for parsing raw unstructured invoice text (use topai_invoice_extractor first, then pass extracted numbers here). Stateless, read-only, idempotent calculation.
Inputs: operation (required), items, amount, rate_percent.
topai_mcp_hub_registryARead-onlyIdempotent
Introspects and searches the TopAI Sovereign Gateway catalog of MCP tools by functional category or keyword. Use when an autonomous agent wants to discover which specialized tools are available on this hub before selecting one. Do not use to execute a domain tool directly—call the specific topai_* tool once identified. Stateless, read-only, idempotent registry lookup.
Inputs: search, category.
topai_openapi_flattenerARead-onlyIdempotent
Dereferences internal and external $ref pointers, neutralizes circular schema references, and flattens OpenAPI 3.0/3.1 specifications into a self-contained JSON document. Use before importing complex OpenAPI specs into RapidAPI, Postman, or LLM function-calling compilers that reject nested $ref pointers. Do not use for general JSON token minification (use topai_token_slimmer instead). Stateless, read-only, idempotent schema transformation.
Inputs: spec_url, spec_json.
topai_pharmapatent_watcherARead-onlyIdempotent
Retrieves pharmaceutical patent cliff dates, active ingredient metadata, FDA Orange Book / European exclusivity expirations, and generic entry threat levels for a given drug name. Use for life-sciences competitive intelligence, LOE (Loss of Exclusivity) forecasting, and pharmaceutical IP analysis. Do not use for verifying individual physician NPI medical licenses (use topai_healthcare_validator instead). Stateless, read-only, idempotent lookup.
Inputs: drug_name (required), jurisdiction.
topai_polymarket_arbitrageARead-onlyIdempotent
Computes prediction market implied probability, mispricing delta, expected value (EV%), and fractional Kelly criterion position sizing between a Polymarket contract price and a reference benchmark probability. Use for quantitative prediction market analysis, odds comparison, and risk-adjusted bankroll allocation. Do not use for standard VAT or invoice accounting (use topai_math_fact_checker instead). Stateless, read-only, idempotent quantitative calculator.
Inputs: polymarket_price (required), reference_probability (required), bankroll_usd.
topai_prompt_shieldARead-onlyIdempotent
Scans user prompts or untrusted external text in <1ms to detect adversarial prompt injections, jailbreak attempts, toxic payloads, and PII leakage. Use as a pre-inference security guardrail before passing untrusted user input or scraped web content to an LLM. Do not use for compressing safe prompts (use topai_token_slimmer instead). Stateless, read-only, idempotent security evaluation returning a boolean safety verdict and threat score (0.0 to 1.0).
Inputs: prompt (required).
topai_semantic_cacheAIdempotent
Performs sub-5ms semantic vector cache lookups ('get') and completions storage ('set') for LLM prompts to eliminate redundant inference latency and token spend. Use before invoking an expensive upstream LLM to check if an equivalent prompt was already answered, or right after generation to cache the completion. Do not use for compressing raw text length within a single uncached prompt (use topai_token_slimmer instead). Idempotent, non-destructive edge cache operation.
Inputs: action (required), prompt (required), response.
topai_techstack_fingerprintARead-onlyIdempotent
Fingerprints a web domain in <50ms across 70+ technology signatures to identify its CMS, e-commerce engine, analytics stack, CDN, and frontend frameworks. Use when qualifying technical architecture or detecting whether a site runs Shopify, Stripe, HubSpot, Next.js, or Cloudflare. Do not use when you need general workforce size or executive firmographics (use topai_company_enrichment instead). Stateless, read-only, idempotent inspection.
Inputs: domain (required).
topai_token_slimmerARead-onlyIdempotent
Compresses bloated HTML, JSON, or plain-text payloads losslessly to reduce LLM input token consumption by 30% to 70% without losing semantic meaning. Use before sending large JSON API responses, logs, or RAG chunks into an LLM context window. Do not use for converting a live URL directly into Markdown (use topai_web_to_markdown instead) or for caching full prompt completions (use topai_semantic_cache instead). Stateless, read-only, idempotent compression.
Inputs: content (required), format.
topai_web_to_markdownARead-onlyIdempotent
Converts any public HTTP/HTTPS webpage into clean, ad-free, token-optimized Markdown with document metadata. Use when an agent needs to read article text, documentation, or web pages without HTML/DOM clutter before RAG indexing or summarization. Do not use for capturing visual pixel screenshots (use topai_headless_screenshot instead) or running multi-site keyword searches (use topai_ai_web_search instead). Stateless, read-only, idempotent execution in <30ms.
Inputs: url (required), include_links.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 19 tools
Every tool has a clearly distinct purpose, reinforced by explicit 'Do not use ... instead' cross-references in descriptions. Overlaps are minimal and well-handled (e.g., search vs markdown conversion vs AI Overview extraction).
All tools follow a consistent topai_ prefix and snake_case naming pattern. The convention is predictable and uniform across the set.
19 tools is slightly above the ideal 3-15 range, but appropriate for a 'universal hub' meant to aggregate many specialized utilities. Each tool earns its place; no obvious filler.
The hub covers a broad range of stateless read-only utilities (web, search, security, data enrichment, text compression, math, vision). While no single domain has full CRUD, the set is coherent for a utility hub and includes a registry tool for discovering more.
Maintenance
Related MCP Connectors
17 pay-per-call web, finance, legal and onchain tools for AI agents. USDC on Base via x402/MPP.
Verified, pay-per-use API tools for AI agents through one authenticated connection.
70+ pay-per-call tools for AI agents: web search, email verify, KYC, stocks, crypto, news, data
Pay-per-call tools for AI agents, paid in USDC on Base or Solana. Web search, page and PDF reading, crypto news, Hyperliquid perps, market pulse, Chainlink price history, token checks, SEC filings, weather and more. Free calls every day, and a failed call costs nothing. Works with Tollkit Wallet.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceEnables AI agents to dynamically discover and invoke containerized tools that can be registered at runtime without redeployment. Built on Cloudflare Workers with scale-to-zero containers for secure, isolated tool execution.-
- AlicenseNot gradedqualityNot gradedmaintenanceEnables AI assistants to control a web browser through tools for navigation, clicking, typing, and capturing screenshots using Cloudflare Workers. It allows models to perform complex web automation tasks and interact with live websites through a set of 14 specialized tools.Apache 2.0
- FlicenseNot gradedqualityBmaintenanceProvides 63 production-ready API tools for AI agents, including web scraping, AI generation, crypto data, OCR, image generation, audio transcription, text-to-speech, email, and domain lookup.3-
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to validate AI infrastructure claims, check endpoint availability, solve CAPTCHA challenges, convert web pages to Markdown, search the web, extract structured JSON, and fetch bot-protected HTML through native tool calls.MIT