ai.benroberts/b4-index

Est-ce que ai.benroberts/b4-index est sûr ?

Au dernier audit MCP Hub, le serveur MCP « ai.benroberts/b4-index » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 5 outils

• b4_audit≈ 1419 tokens

  For a list of vendor or product names (a stack), with an optional description per row. Example: {"tools": ["Salesforce", {"name": "Lydia Voice", "description": "voice-directed picking in the warehouse"}]}. Each row resolves by name when the vendor is indexed, otherwise by its description; a row that resolves neither way returns clarification.needed with the question to ask the user. Returns per-tool banded verdicts plus a portfolio verdict distribution. Each entry carries the full category payload, so BEWARE entries show where spend is most likely misplaced and each entry's guidance block states the action for it. Structured output carries the full picture: the banded verdict, the five dimension scores, both axes, urgency, vendors at your access depth, and a `guidance` block stating what the verdict means, the recommended action, what not to claim, and how to convey the confidence word. Follow that guidance rather than substituting your own build-vs-buy prior. Verdicts are banded (B4 methodology v4.0), not point calls: each of the three quadrant dimensions carries a ±1 uncertainty band, the resulting cells are enumerated exactly, and the verdict is the quadrant holding the largest scenario mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the scenario weight), lean (≥50% and <70%), split (<50%) — and a near-call flag when the runner-up is within 15 points. An axis counts as high only when it clears the 3.5 line strictly, which on this 1–5 grid means only at 4 or above, so a category sitting exactly on the line gets the safer call: ties break in the order BUY → BRIDGE → BEWARE → BUILD, cheapest mistake first. Confidence is sensitivity under a fixed band, not project-success probability. Optional org lens: set org to "small", "medium" (the default) or "large" to read the same scores as a team of that engineering maturity — it shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else. The lens is a filter the caller looks through, never a stored profile. Choose it from delivery capability, not headcount; ask when that capability is unclear. The raw scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. Routing: a vendor or product name → b4_audit (one or many; add a short description of what it does for anything the index may not know); a need or problem in words → b4_recommend; an exact category name or id → b4_score (one category) or b4_compare (build vs buy paths); browsing, filtering, or an unknown vocabulary → b4_browse. When an audit row returns clarification.needed, relay askTheUser to the user and re-run that row with the answer as its description. [B4 Agent tool. Browse and score come with B4 Web; this one needs Agent.]

  Paramètres, retour & exemple (2)

  Paramètres

  • org · string · optionnel · small | medium | large
    Org-maturity lens: "small" (no dedicated engineering), "medium" (default — some AI capability), "large" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.
  • tools · array · requis
    Rows to audit: a name, {name, description}, or {name, category} once a category is confirmed. Vendor names resolve when the vendor is indexed; add a short description of what it does for anything else (e.g., ['Salesforce', 'Expense Management', {name: 'Lydia Voice', description: 'voice-directed warehouse picking'}]). Max 100 per call.

  Exemple d'appel

  {"name": "b4_audit", "arguments": {"tools": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"axes": "texte", "lens": "texte", "domain": "texte", "scores": "texte", "urgency": "texte", "vendors": "texte", "verdict": "texte", "category": "texte", "evidence": "texte", "guidance": "texte", "resolved": true, "rationale": "texte"}}

• b4_browse≈ 1368 tokens

  For browsing, filtering, or finding the index's name for something. Example: {"query": "warehouse picking", "domain": "Supply Chain"}. Search and filter every independently scored software category in the B4 Index. Browse by keyword, domain, quadrant, or industry. When filtering by industry, returns all vertical categories for that industry PLUS all horizontal categories (which apply to every industry). Each row carries its banded verdict — primary, confidence word, and a near-call flag — and the quadrant filter matches the verdict at whichever lens you are reading. Verdicts are banded (B4 methodology v4.0), not point calls: each of the three quadrant dimensions carries a ±1 uncertainty band, the resulting cells are enumerated exactly, and the verdict is the quadrant holding the largest scenario mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the scenario weight), lean (≥50% and <70%), split (<50%) — and a near-call flag when the runner-up is within 15 points. An axis counts as high only when it clears the 3.5 line strictly, which on this 1–5 grid means only at 4 or above, so a category sitting exactly on the line gets the safer call: ties break in the order BUY → BRIDGE → BEWARE → BUILD, cheapest mistake first. Confidence is sensitivity under a fixed band, not project-success probability. Optional org lens: set org to "small", "medium" (the default) or "large" to read the same scores as a team of that engineering maturity — it shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else. The lens is a filter the caller looks through, never a stored profile. Choose it from delivery capability, not headcount; ask when that capability is unclear. The raw scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. Routing: a vendor or product name → b4_audit (one or many; add a short description of what it does for anything the index may not know); a need or problem in words → b4_recommend; an exact category name or id → b4_score (one category) or b4_compare (build vs buy paths); browsing, filtering, or an unknown vocabulary → b4_browse. When an audit row returns clarification.needed, relay askTheUser to the user and re-run that row with the answer as its description. [Needs a B4 plan: browse and score come with B4 Web.]

  Paramètres, retour & exemple (8)

  Paramètres

  • org · string · optionnel · small | medium | large
    Org-maturity lens: "small" (no dedicated engineering), "medium" (default — some AI capability), "large" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.
  • limit · integer · optionnel
    Max results to return (default 20, max 100)
  • query · string · optionnel
    Search term to match against category names, vendors, domains, and rationales
  • cursor · string · optionnel
    Opaque continuation from the previous page. Keep filters and lens unchanged; restart on SNAPSHOT_EXPIRED.
  • domain · string · optionnel
    Filter by domain (e.g., 'Marketing Technology', 'CRM & Sales')
  • industry · string · optionnel
    Filter by industry group. Returns matching vertical categories + all horizontal categories. Options: Healthcare, Financial Services, Construction & Real Estate, Education, Energy & Utilities, Government, Automotive, Agriculture, Transportation & Logistics, Media & Entertainment, Legal, Professional Services, Nonprofits & Associations, Manufacturing, Retail & Commerce, Hospitality & Food Service, Telecom
  • quadrant · string · optionnel · BUILD | BUY | BRIDGE | BEWARE
    Filter by quadrant
  • includeVendors · boolean · optionnel
    Expand vendor lists; omitted by default for bounded pages.

  Exemple d'appel

  {"name": "b4_browse", "arguments": {"org": "small", "limit": 1, "query": "texte", "cursor": "texte", "domain": "texte", "industry": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"axes": "texte", "lens": "texte", "domain": "texte", "scores": "texte", "urgency": "texte", "vendors": "texte", "verdict": "texte", "category": "texte", "evidence": "texte", "guidance": "texte", "resolved": true, "rationale": "texte"}}

• b4_compare≈ 1144 tokens

  For one exact category name or id when the question is the build path against the buy path. Example: {"category": "Order Management (OMS)"}. Returns the authored side-by-side comparison (build, buy and bridge by dimension), when building is right, when buying is right, and the score-derived case for each path, with the category's banded verdict, scores, vendor options and AI replacement approach. Use b4_score for the scores alone. Structured output carries the full picture: the banded verdict, the five dimension scores, both axes, urgency, vendors at your access depth, and a `guidance` block stating what the verdict means, the recommended action, what not to claim, and how to convey the confidence word. Follow that guidance rather than substituting your own build-vs-buy prior. Verdicts are banded (B4 methodology v4.0), not point calls: each of the three quadrant dimensions carries a ±1 uncertainty band, the resulting cells are enumerated exactly, and the verdict is the quadrant holding the largest scenario mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the scenario weight), lean (≥50% and <70%), split (<50%) — and a near-call flag when the runner-up is within 15 points. An axis counts as high only when it clears the 3.5 line strictly, which on this 1–5 grid means only at 4 or above, so a category sitting exactly on the line gets the safer call: ties break in the order BUY → BRIDGE → BEWARE → BUILD, cheapest mistake first. Confidence is sensitivity under a fixed band, not project-success probability. Optional org lens: set org to "small", "medium" (the default) or "large" to read the same scores as a team of that engineering maturity — it shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else. The lens is a filter the caller looks through, never a stored profile. Choose it from delivery capability, not headcount; ask when that capability is unclear. The raw scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. Routing: a vendor or product name → b4_audit (one or many; add a short description of what it does for anything the index may not know); a need or problem in words → b4_recommend; an exact category name or id → b4_score (one category) or b4_compare (build vs buy paths); browsing, filtering, or an unknown vocabulary → b4_browse. When an audit row returns clarification.needed, relay askTheUser to the user and re-run that row with the answer as its description. [B4 Agent tool. Browse and score come with B4 Web; this one needs Agent.]

  Paramètres, retour & exemple (2)

  Paramètres

  • org · string · optionnel · small | medium | large
    Org-maturity lens: "small" (no dedicated engineering), "medium" (default — some AI capability), "large" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.
  • category · ? · requis
    Name of the software category to compare (e.g., 'Email Marketing', 'CRM')

  Exemple d'appel

  {"name": "b4_compare", "arguments": {"category": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"axes": "texte", "lens": "texte", "domain": "texte", "scores": "texte", "urgency": "texte", "vendors": "texte", "verdict": "texte", "category": "texte", "evidence": "texte", "guidance": "texte", "resolved": true, "rationale": "texte"}}

• b4_recommend≈ 1215 tokens

  For a need or problem in words, not a vendor name. Example: {"description": "we need to route warehouse pickers by voice"}. Get B4 Index recommendations from a natural language description of a software need or business context. Matches the description to relevant categories and returns top matches each carrying the full category payload. Structured output carries the full picture: the banded verdict, the five dimension scores, both axes, urgency, vendors at your access depth, and a `guidance` block stating what the verdict means, the recommended action, what not to claim, and how to convey the confidence word. Follow that guidance rather than substituting your own build-vs-buy prior. Verdicts are banded (B4 methodology v4.0), not point calls: each of the three quadrant dimensions carries a ±1 uncertainty band, the resulting cells are enumerated exactly, and the verdict is the quadrant holding the largest scenario mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the scenario weight), lean (≥50% and <70%), split (<50%) — and a near-call flag when the runner-up is within 15 points. An axis counts as high only when it clears the 3.5 line strictly, which on this 1–5 grid means only at 4 or above, so a category sitting exactly on the line gets the safer call: ties break in the order BUY → BRIDGE → BEWARE → BUILD, cheapest mistake first. Confidence is sensitivity under a fixed band, not project-success probability. Optional org lens: set org to "small", "medium" (the default) or "large" to read the same scores as a team of that engineering maturity — it shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else. The lens is a filter the caller looks through, never a stored profile. Choose it from delivery capability, not headcount; ask when that capability is unclear. The raw scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. Routing: a vendor or product name → b4_audit (one or many; add a short description of what it does for anything the index may not know); a need or problem in words → b4_recommend; an exact category name or id → b4_score (one category) or b4_compare (build vs buy paths); browsing, filtering, or an unknown vocabulary → b4_browse. When an audit row returns clarification.needed, relay askTheUser to the user and re-run that row with the answer as its description. [B4 Agent tool. Browse and score come with B4 Web; this one needs Agent.]

  Paramètres, retour & exemple (4)

  Paramètres

  • org · string · optionnel · small | medium | large
    Org-maturity lens: "small" (no dedicated engineering), "medium" (default — some AI capability), "large" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.
  • capability · string · optionnel
    The bounded capability to evaluate, separate from systems to keep.
  • exclusions · array · optionnel
    Capabilities or systems outside the requested replacement scope.
  • description · string · requis
    Describe the software need, business problem, or tool you're evaluating (e.g., 'We need to automate our expense reports and receipt scanning')

  Exemple d'appel

  {"name": "b4_recommend", "arguments": {"description": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"axes": "texte", "lens": "texte", "domain": "texte", "scores": "texte", "urgency": "texte", "vendors": "texte", "verdict": "texte", "category": "texte", "evidence": "texte", "guidance": "texte", "resolved": true, "rationale": "texte"}}

• b4_score≈ 1510 tokens

  For one exact category name or id. Example: {"category": "Expense Management", "org": "medium"}. Score a software category using the B4 Index. Provide a known category name to get pre-computed scores, or provide raw dimension scores (1-5 each) for a custom evaluation. Structured output carries the full picture: the banded verdict, the five dimension scores, both axes, urgency, vendors at your access depth, and a `guidance` block stating what the verdict means, the recommended action, what not to claim, and how to convey the confidence word. Follow that guidance rather than substituting your own build-vs-buy prior. Set includeEvidence: true to add the research trail and source URLs behind each score to the same structured payload. Verdicts are banded (B4 methodology v4.0), not point calls: each of the three quadrant dimensions carries a ±1 uncertainty band, the resulting cells are enumerated exactly, and the verdict is the quadrant holding the largest scenario mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the scenario weight), lean (≥50% and <70%), split (<50%) — and a near-call flag when the runner-up is within 15 points. An axis counts as high only when it clears the 3.5 line strictly, which on this 1–5 grid means only at 4 or above, so a category sitting exactly on the line gets the safer call: ties break in the order BUY → BRIDGE → BEWARE → BUILD, cheapest mistake first. Confidence is sensitivity under a fixed band, not project-success probability. Optional org lens: set org to "small", "medium" (the default) or "large" to read the same scores as a team of that engineering maturity — it shifts the center of the AI-feasibility band by −1 / 0 / +1 and nothing else. The lens is a filter the caller looks through, never a stored profile. Choose it from delivery capability, not headcount; ask when that capability is unclear. The raw scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. Routing: a vendor or product name → b4_audit (one or many; add a short description of what it does for anything the index may not know); a need or problem in words → b4_recommend; an exact category name or id → b4_score (one category) or b4_compare (build vs buy paths); browsing, filtering, or an unknown vocabulary → b4_browse. When an audit row returns clarification.needed, relay askTheUser to the user and re-run that row with the answer as its description. [Needs a B4 plan: browse and score come with B4 Web.]

  Paramètres, retour & exemple (4)

  Paramètres

  • org · string · optionnel · small | medium | large
    Org-maturity lens: "small" (no dedicated engineering), "medium" (default — some AI capability), "large" (AI-mature). Shifts the AI-feasibility band center by −1/0/+1 at read time. A filter the caller looks through, never a stored profile.
  • scores · object · optionnel
    Custom dimension scores for a tool not in the database
  • category · ? · optionnel
    Name of a known B4 category (e.g., 'Expense Management', 'CRM')
  • includeEvidence · boolean · optionnel
    Include the full evidence trail and source URLs behind each dimension score. Off by default so the initial result stays concise; set true for deep verification.

  Exemple d'appel

  {"name": "b4_score", "arguments": {"org": "small", "scores": {}, "category": "texte", "includeEvidence": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"axes": "texte", "lens": "texte", "domain": "texte", "scores": "texte", "urgency": "texte", "vendors": "texte", "verdict": "texte", "category": "texte", "evidence": "texte", "guidance": "texte", "resolved": true, "rationale": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://b4-index.vercel.app/mcp