About io.github.Craig-Horton/aibvf-mcp
io.github.Craig-Horton/aibvf-mcp is an MCP server in the RAG category: aI BVF: score AI portfolios Stop/Fix/Accelerate with decision confidence and pace-layer drag.
Install
Claude Code
claude mcp add io-github-craig-horton-aibvf-mcp -- npx -y aibvf-mcpnpx
npx -y aibvf-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (13)
assemble_portfolioAssembles a valid BVF v1.0 portfolio document from loose inputs: names, plain-language functions and tiers, and whatever pillar scores exist. Aliases resolved, ids generated, missing pillars estimated with the estimation reported per initiative, document validated before return. Nothing stored, nothing edited.
Parameters not published.
assess_ai_initiativePlain-English front door for one AI decision: resolves the five scoring inputs, tests the work architecture, asks one question when something is missing, then returns the verdict.
Parameters not published.
calculate_pace_layer_dragAnnual Organisational Drag Cost in EUR from AI-tier vs operating-model misalignment.
Parameters not published.
diagnose_processAI BVF Advisor Brain: diagnoses one business process from observed signals (volume, labour, cycle time, handoffs, rework, automation, spend) and returns heaviness, intervention, net EUR saving, efficiency gain, verdict, and decision confidence.
Parameters not published.
get_benchmarkLooks up the disclosed AI BVF planning rates for a business function and industry, with evidence status and use guidance.
Parameters not published.
infer_readinessMeasures organisational readiness from process signals (hand-offs, rework, touch ratio, automation, cycle time vs function medians) instead of accepting self-report. Returns the classification the data supports, per-signal reasoning, and a confidence set by coverage and agreement. When the measured answer is lower than the claimed one, that gap is itself a change-readiness finding.
Parameters not published.
list_taxonomyReturns valid values for industries, functions, AI tiers, readiness levels.
Parameters not published.
map_to_taxonomyMaps everyday business language (customer service, procurement, banking, GenAI copilot, bureaucratic) onto the canonical enums, deterministically, with suggestions instead of guesses when there is no confident match.
Parameters not published.
recommend_improvementsFor Stop or Fix, returns the pillar raises and named change plays, including workflow and role redesign when the work architecture has a gap.
Parameters not published.
score_initiativeFour-pillar score plus a work architecture gate returns Accelerate, Fix, or Stop with EUR value range, decision confidence, applied modules and reasoning.
Parameters not published.
Show all 13 tools
score_portfolioScores every initiative in a BVF portfolio in one call and returns the board-level shape: Accelerate/Fix/Stop counts, aggregate EUR value, mean decision confidence, top initiative by value, highest-risk initiative.
Parameters not published.
sequence_portfolioTurns a scored portfolio into a three-wave rollout plan with named gates: Stops first (free the budget), quick Accelerates second (buy trust), complex work and Fixes third. Enforces change capacity per function, because ten good ideas can still break an organisation if they all land in one place.
Parameters not published.
validate_portfolioValidates a portfolio JSON document against the BVF v1.0 schema.
Parameters not published.
Ask AI
✦
Ask AI about io.github.Craig-Horton/aibvf-mcp
Powered by Claude · Grounded in docs
I know everything about io.github.Craig-Horton/aibvf-mcp. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.