mcp server

B4 Index

Independent build-vs-buy index: score software categories BUILD/BUY/BRIDGE/BEWARE.

Description as published by the maintainer. Source

• version 3.3.0
• active

active — Registry entry last updated 2026-07-03.

What this server can do

5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

b4_audit(org, tools)

Analyze a software stack against the B4 Index. Provide a list of tool/category names, and get per-tool banded verdicts plus a portfolio summary with verdict distribution, BEWARE spend, near calls, and priority actions. 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 most probability mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the mass), lean (50–70%), 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. 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: no user attribute is saved, inferred, or asked for, and the scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. [B4 Agent — the free tools are b4_browse and b4_score.] Required: tools.

b4_browse(org, limit, query, domain, industry, quadrant)

Search and filter the B4 Index's 1,600+ independently scored software categories. 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 most probability mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the mass), lean (50–70%), 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. 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: no user attribute is saved, inferred, or asked for, and the scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces.

b4_compare(org, category)

Compare build vs buy for a specific software category. Returns side-by-side analysis with the category's banded verdict, scores, vendor options, AI replacement approach, and action steps for each path. 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 most probability mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the mass), lean (50–70%), 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. 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: no user attribute is saved, inferred, or asked for, and the scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. [B4 Agent — the free tools are b4_browse and b4_score.] Required: category.

b4_recommend(org, description)

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 with scores, banded verdicts, and actionable recommendations. 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 most probability mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the mass), lean (50–70%), 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. 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: no user attribute is saved, inferred, or asked for, and the scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces. [B4 Agent — the free tools are b4_browse and b4_score.] Required: description.

b4_score(org, scores, category, includeEvidence)

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. Returns the banded verdict (primary, confidence, near-call flag, full distribution, tipping point), axes, urgency level, and a concise breakdown. The default result is intentionally lean — set includeEvidence: true to also get the full research trail and source URLs behind each score. 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 most probability mass. Every verdict ships with its full distribution, a confidence word — clear (≥70% of the mass), lean (50–70%), 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. 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: no user attribute is saved, inferred, or asked for, and the scores themselves never change. Omit it and you get the default-lens numbers, which are the ones published on logged-out surfaces.

Last successful function declaration observed on 2026-08-13. Source: https://b4-index.vercel.app/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://b4-index.vercel.app/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Website — https://benroberts.ai/directory
• Remote endpoint (streamable-http) — https://b4-index.vercel.app/mcp