io.github.aaronmsoto/finops-framework-mcp

For one capability, the official maturity assessment text at each level between current and target — evidence to look for when maturing. To get one level's assessment text on its own (or all three at once), use get_maturity_assessment instead.

One capability's content, section-selectable via `include` to control size. Default include is [summary, definition] (~1-2k tokens). Approximate extra cost per section: maturity ~2.5k tokens, activities ~3k (filter with `persona`), kpis ~1k, headline_groups/inputs_outputs <1k; requesting ALL sections is roughly 7k tokens — prefer the finops://framework/capabilities/{slug} resource for the full document.

What changed between data versions of this server's crawled artifact (rolling window of the 20 most recent refreshes — the crawler caps the log at 20, so this tool covers the full retained history; the same data is at finops://framework/meta/changelog). Reflects crawl-to-crawl differences in finops.org content, not a Foundation-published changelog.

Full rendered markdown for entity types that have no dedicated tool. Required param: `entity_type` (principles | phases | domains | technology-categories | scopes | persona). Collections return whole (they are small); entity_type 'persona' also needs `slug`. For capabilities use get_capability; for KPIs get_kpis; for maturity levels get_maturity_model.

Start here. Returns the framework's structure (entity counts), the data version/crawl date/license, and how to navigate this server's tools. No parameters.

Full KPI records: description, formula + candidate data sources (present for the 44 KPIs the site details in capability-page popups), official related capabilities, and where each is featured. Look up one KPI with `slug`, or filter by capability and/or featured_only — filters combine (AND), so a `slug` that doesn't match the `capability` filter returns zero records. Without filters, pages through the whole 88-entry library.

The official FinOps Framework maturity assessment prose for a capability, verbatim, at one level (crawl|walk|run) or all three. This is the Foundation's published assessment text, not a parsed breakdown.

The official FinOps maturity model: Crawl/Walk/Run with each level's characteristics and the community's sample goals/KPIs (e.g. allocation coverage targets per level). Capability-agnostic — for one capability's per-level assessment use get_maturity_assessment.

All 22 capabilities (slug, title, domain, one-line summary), optionally filtered by `domain` and/or `persona` (both take a slug, e.g. domain="understand-usage-and-cost", persona="finance"). The framework does not assign capabilities to phases, so there is deliberately no phase filter. Default limit returns the full list in one call.

With `persona`: every capability that persona works in, WITH that persona's activity bullets inline (one call answers 'what does X do across the framework'). With `capability`: every persona active in it, with activities. With neither: the full persona index (slugs, categories) — use it to discover persona slugs. Passing both is an error — pick one direction per call. Allied personas are mapped at group level by the framework; responses say so explicitly.

Ranked keyword search over every entity (capabilities, KPIs, personas, principles, phases, domains, technology categories, maturity levels, scopes). Returns slug + uri per hit. Feed the slug to `get_kpis(slug: …)`, or pass it as `capability: <slug>` to get_capability/get_maturity_assessment/assess_maturity_path/map_personas and as `persona: <slug>` where a persona filter is accepted. Other entity types (principles, phases, domains, technology categories, scopes) are read via get_entity(entity_type: …) or the hit's finops:// resource uri. Use this whenever you don't already know a slug.