Wizeb AI-Native Index MCP server
com.wizeb/ai-native-indexwizeb.comstreamable-httpv1.2.0Scanned
AI-Native Index scoring, PDF report, Wizeb Q&A, and an Enhanced report agents buy over x402.
10 tools: 6 change things and 4 only read.
- Reads private data · 1
- Reads text others write · 4
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Wizeb AI-Native Index MCP server can do
The Wizeb AI-Native Index MCP server is published by wizeb.com, a domain the MCP Registry verified. It has 10 tools. It can create or change data (6 tools: score_index, email_index_report, get_enhanced_index_report, score_startup_idea and 2 more), but cannot delete data. 4 tools only read.
1 tool reads private data (list_wizeb_services_and_products); 4 tools bring in text other people can write (email_index_report, get_enhanced_index_report, email_startup_scorecard and 1 more).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 1.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
10 tools
Changes things 6Claude Code: ask
ask_about_wizebAnswers questions about WizeB — what it builds (custom AI agents, workflow automation, voice AI, document AI, web & mobile apps, AI cost/token optimisation, database reactivation),…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
email_index_reportBuilds 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, wi…Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
email_startup_scorecardEmails a scorecard created with score_startup_idea to the founder, with a copy to the WizeB team so a human can follow up.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
get_enhanced_index_reportPAID TOOL — $10 in USDC on Base, settled over the x402 protocol from the calling agent's wallet.Reads text others write1 finding
Why it is in this group
- The name "get_enhanced_index_report" says "get": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Findings
- Warn
The server marks "get_enhanced_index_report" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"idempotentHint":false,"openWorldHint":true}; The name "get_enhanced_index_report" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: true
score_indexScores a complete set of 30 answers and returns the index (0–100), tier, per-dimension scores, strengths, and the signals holding the company back.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
score_startup_ideaTotals 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…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: false
- idempotentHint: false
- openWorldHint: false
Only reads 4Show 4 read-only tools
get_enhanced_report_statusFree.No findings
Why it is in this group
- The name "get_enhanced_report_status" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_index_questionsReturns the six dimensions and all 30 questions with their numbered answer options (1 = least AI-native, highest number = fully AI-native).No findings
Why it is in this group
- The name "get_index_questions" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
get_startup_validator_rubricReturns 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…No findings
Why it is in this group
- The name "get_startup_validator_rubric" says "get": a word for reading.
Description, as the server wrote it 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.
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
list_wizeb_services_and_productsReturns 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 t…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_wizeb_services_and_products" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "return" and "contact": it reads contacts.
- untrusted-inputThe description's first sentence says "return" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it 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".
Annotations the server declares
- readOnlyHint: true
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:50 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://wizeb.com/mcp: tools/list returned 10 tools to an anonymous client, including score_index (write), email_index_report (write), get_enhanced_index_report (write), score_startup_idea (write), email_startup_scorecard (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
The server marks "get_enhanced_index_report" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"idempotentHint":false,"openWorldHint":true}; The name "get_enhanced_index_report" says "get": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http ai-native-index https://wizeb.com/mcpclaude mcp add --transport http ai-native-index https://wizeb.com/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__ai-native-index__get_index_questions",
"mcp__ai-native-index__get_enhanced_report_status",
"mcp__ai-native-index__get_startup_validator_rubric",
"mcp__ai-native-index__list_wizeb_services_and_products"
],
"ask": [
"mcp__ai-native-index__score_index",
"mcp__ai-native-index__email_index_report",
"mcp__ai-native-index__get_enhanced_index_report",
"mcp__ai-native-index__score_startup_idea",
"mcp__ai-native-index__email_startup_scorecard",
"mcp__ai-native-index__ask_about_wizeb"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as ai-native-index. Review it before you use it.
Capability tags behind 4 rules
- mcp__ai-native-index__email_index_report untrusted-input
- mcp__ai-native-index__get_enhanced_index_report untrusted-input
- mcp__ai-native-index__email_startup_scorecard untrusted-input
- mcp__ai-native-index__list_wizeb_services_and_products private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/com.wizeb/ai-native-index/verify?hash=4693c8e0d7b09b0f7073e27663a2c3aa867f71ec4debf006256de5450208e6b1" | jq -e '.changed == false'Pinned hash 4693c8e0d7b0, from Nov 11, 2026, 06:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.wizeb/ai-native-index/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.wizeb/ai-native-index)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:11 UTC.
Wizeb AI-Native Index MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Wizeb AI-Native Index MCP server safe?
- No scan can promise that. What its definitions show: 10 tools, 6 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Wizeb AI-Native Index MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Wizeb AI-Native Index MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Wizeb AI-Native Index MCP server have?
- 10 tools: 6 write, 4 read. score_index, email_index_report, get_enhanced_index_report, score_startup_idea, email_startup_scorecard, ask_about_wizeb, get_index_questions, get_enhanced_report_status and 2 more.
Does the Wizeb AI-Native Index MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Wizeb AI-Native Index MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Wizeb AI-Native Index MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.