Wizeb AI-Native Index

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

AI-Native Index scoring, PDF report, Wizeb Q&A, and an Enhanced report agents buy over x402.

Measured statistics

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Wizeb AI-Native Index": {
      "url": "https://wizeb.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (10)

• get_index_questions read-only

  Returns the six dimensions and all 30 questions with their numbered answer options (1 = least AI-native, highest number = fully AI-native). Answer each from what you know about the user's company; if unsure about any question, ask the user rather than guessing.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• score_index

  Scores a complete set of 30 answers and returns the index (0–100), tier, per-dimension scores, strengths, and the signals holding the company back. Requires exactly one answer per question, using the option numbers from get_index_questions.

  Parameters:

  • answers (required) — array — One entry per question id 1–30.
  • company_website — string — The company's website, if you know it (optional)

  Hints: read-only no · destructive not declared · idempotent no · open-world no

• email_index_report

  Builds the full PDF scorecard (score, tier, six-dimension breakdown, every answer next to the AI-native end state, and the three fastest improvements) and emails it to the user, with a copy to the WizeB team so a human can follow up. Ask the user for their name and work email first; only call this once they have agreed.

  Parameters:

  • name (required) — string — The user's name
  • email (required) — string — The user's work email address
  • answers (required) — array — The same 30 answers passed to score_index.
  • run_id — string — The run_id returned by score_index, so the saved run is updated rather than duplicated
  • company — string — Company name (optional)
  • company_website — string — The company's website (optional)

  Hints: read-only no · destructive not declared · idempotent no · open-world yes

• get_enhanced_index_report

  PAID TOOL — $10 in USDC on Base, settled over the x402 protocol from the calling agent's wallet. Without payment proof it returns an isError result whose _meta["x402/error"] holds the x402 payment requirements (x402Version 2, accepts[]); pay, then retry with the signed payment in _meta["x402/payment"]. Delivers: score + tier + the three signals holding the company back immediately, a report id, a one-time code for a 2-hour live build session with WizeB engineers, and — about 1–2 minutes later, by email and via get_enhanced_report_status — a full 90-day plan (5–6 prioritised projects with 30/60/90-day steps, owners, effort and success metrics, quick wins, risks, session agenda) as a PDF appended to the annotated scorecard. Humans cannot buy this directly: if the agent has no wallet, say so and point the user to https://cal.id/r/discovery (WizeB helps set one up) and https://wizeb.com/ai-native-index/agent-payments. Ask the user before spending their money.

  Parameters:

  • name (required) — string — The user's name
  • email (required) — string — Work email — the report PDF and session code are sent here
  • answers (required) — The same 30 answers passed to score_index — an array of { id, option }, or the 30 option digits as a string.
  • company — string — Company name (optional but improves the plan)

  Hints: read-only no · destructive not declared · idempotent no · open-world yes

• get_enhanced_report_status read-only

  Free. Returns the status of a purchased enhanced report by report_id (payment confirming → paid → generating → done; while confirming, do not pay again), the plan summary and PDF link once done, the session booking code, and the payment receipt.

  Parameters:

  • report_id (required) — string — The report_id returned by get_enhanced_index_report

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• get_startup_validator_rubric read-only

  Returns the Startup Idea Validator rubric: the 10 weighted patterns from NFX's "Hidden Patterns of Great Startup Ideas" with scoring anchors, the red flags and their penalties, the verdict zones, and how to interview the founder. Call this first, then interview the founder one question at a time and call score_startup_idea.

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• score_startup_idea

  Totals a startup idea scorecard you wrote with the rubric from get_startup_validator_rubric: clamps each pattern to its maximum, applies red-flag penalties (capped at 15), sets the verdict (Mediocre under 55, Not sure 55-74, Fertile soil 75+), stores it, and returns a report_id plus a result link the founder can open and share. Pass all 10 pattern ids. Links in free text are removed.

  Parameters:

  • idea_name (required) — string — Product or company name, or a 2-4 word name for the idea
  • dimensions (required) — array — One entry per pattern id from the rubric.
  • verdict_summary (required) — string — 2-3 sentences: what it is, where it sits, the biggest reason
  • direction (required) — object
  • risks — array
  • website — string — The founder's website, if any
  • working — array
  • reframes — array
  • interview — array — The questions you asked and the founder's answers.
  • red_flags — array
  • confidence — string
  • assumptions — array
  • venture_note — string — Only if the founder wants a lifestyle/bootstrapped business: how to read the score. Otherwise empty.

  Hints: read-only no · destructive not declared · idempotent no · open-world no

• email_startup_scorecard

  Emails a scorecard created with score_startup_idea to the founder, with a copy to the WizeB team so a human can follow up. Ask the founder for their name and email first; only call this once they have agreed.

  Parameters:

  • report_id (required) — string — The report_id returned by score_startup_idea
  • name (required) — string — The founder's name
  • email (required) — string — The founder's email address
  • run_id — string — The run_id returned by score_startup_idea (keeps the founder's saved run as one record)
  • company — string — Company name (optional)

  Hints: read-only no · destructive not declared · idempotent no · open-world yes

• ask_about_wizeb read-only

  Answers questions about WizeB — what it builds (custom AI agents, workflow automation, voice AI, document AI, web & mobile apps, AI cost/token optimisation, database reactivation), its products (RemindAvo, ReviewTaker, Wizot Agent Studio, Orbit, EatRight, TrueTime, Karmic, Voice AI), industries served, case-study results, engagement/pricing/timeline FAQs, open-source tools, recent blog posts, and contact details — and about WebCastle, WizeB's parent company (website, web & mobile app, ERP/CRM/Odoo, e-commerce and IoT development; branding and UI/UX; digital marketing, SEO/GEO, performance marketing; cloud & security; business analysis), including which company to contact for what. Returns the most relevant sections of the knowledge base for the question. Use this instead of answering from memory.

  Parameters:

  • question (required) — string — The user's question about WizeB or WebCastle

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

• list_wizeb_services_and_products read-only

  Returns the full structured catalogue: every WizeB service with its capabilities and URL, every product with URL/pricing, industries served, open-source tools, contact links, and the category-level service catalogue of WebCastle, WizeB's parent company. Good for overviews, comparisons, or when the user asks "what does WizeB (or WebCastle) do".

  Hints: read-only yes · destructive not declared · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.