Cloud FinOps Skill & MCP

Finds runbooks for a suspected cloud-waste pattern, filterable by provider, service, waste category or detection confidence. Useful when the user asks how to detect or fix a specific waste pattern; each runbook includes a detection query the user can run in their own account. This connector has no access to the user's accounts. Use this with ``query`` for a symptom or a "which of my X" question in the user's own words: "our AWS bill has NAT gateway charges but nothing uses them", "which of my RIs are about to expire", "my NAT gateway processes 10TB to S3", "should I delete these old snapshots", "our Log Analytics ingestion doubled", "which VMs are running for nothing", "passerelle NAT qui ne sert à rien". Every runbook declares the questions it answers (English and French); the result is ranked by those, then by title and service, and carries ``matched_question``; the first entry is the one ``get_playbook(name=)`` fetches. Facets narrow the set first; ``query`` ranks what is left. Use this with the facets alone to browse: "what waste can we clean up safely without review" (confidence), "every idle pattern on Azure" (scope and waste category). Patterns covered include NAT gateways and VPC endpoints, expiring Savings Plans / RIs / reservations, snapshot sprawl, S3 lifecycle gaps, idle or stopped VMs, orphaned disks / public IPs / EBS volumes, GPU and SageMaker sizing, Kubernetes idle capacity, and schedule blindness. All filters are optional and combine with AND semantics. String matching is case-insensitive and exact. Examples: - ``find_playbooks(query="which of my RIs are about to expire")`` - ranked runbooks - ``find_playbooks(scope="aws")`` - all AWS-specific playbooks - ``find_playbooks(waste_category="idle")`` - every idle-resource pattern - ``find_playbooks(scope="cross-cloud", confidence="obvious")`` Args: query: the user's symptom or question in their own words, up to 1,000 characters, English or French. Ranks the facet-filtered runbooks by the questions they declare, their title and their service; returns at most five, best first, each with ``match_score`` and ``matched_question`` (a runbook is read whole, so its ``suggested_section`` is null). scope: ``"aws"``, ``"azure"``, ``"gcp"``, or ``"cross-cloud"``. service: Provider service exact-match (e.g. ``"AWS NAT Gateway"``). waste_category: ``"orphaned"``, ``"idle"``, ``"overprovisioned"``, ``"commitment-mismatch"``, ``"schedule-blindness"``, ``"modernization"``, ``"ai-ml-inefficiency"``, or ``"egress"``. confidence: ``"obvious"`` (single signal is enough), ``"likely"`` (two signals required), or ``"possible"`` (needs human review). From the OptimNow three-tier confidence model in `finops-waste-detection-playbooks`. Returns ``{"filters": {...}, "playbooks": [...], "total": N}``. With ``query`` the entries are ranked and capped at five. A facet filter that matches nothing also returns `hint` and `valid_values`, so a typo is distinguishable from a genuine gap in coverage; a ``query`` that matches nothing returns `hint` alone.

Find which guidance serves a FinOps question - how to commit, size, allocate, charge back, forecast, or govern cloud and AI spend. Use this with ``query`` for a question in the user's own words rather than in FinOps Framework terms: "how should we size our first Savings Plan when usage is seasonal", "we hold SQL Server licences with Software Assurance, BYOL or licence-included?", "our forecast missed by 20%", "who should own commitment purchases", "combien s'engager en Savings Plans". Every guide declares the questions it answers (English and French); the result is ranked by those, then by title and section headings, and each entry carries ``matched_question`` and ``suggested_section``, the heading that ``get_reference(name=, section=)`` takes. The facets narrow the set first; ``query`` ranks what is left. Use this with the facets alone for a question already in FinOps Framework terms (domain, capability, phase, persona, maturity): "what does a Crawl-stage org tackle first", "the Engineering reading list", "what should Finance own in chargeback". All filters are optional and combine with AND semantics. Facet matching is case-insensitive and exact (not substring). Examples: - ``find_references(query="our forecast missed by 20%, was it the model or the drivers")`` - ``find_references(domain="Optimize Usage & Cost")`` - ``find_references(phase="Optimize", persona="Engineering")`` - ``find_references(persona="Engineering", persona_primary_only=True)`` - ``find_references(capability="Rate Optimization")`` - ``find_references(maturity="Crawl")`` Args: query: the user's question or symptom in their own words, up to 1,000 characters, English or French. Ranks the facet-filtered guides by the questions they declare, their title and their headings; returns at most five, best first, each with ``match_score``, ``matched_question`` and ``suggested_section``. domain: FinOps Framework domain (e.g. ``"Optimize Usage & Cost"``, ``"Quantify Business Value"``, ``"Manage the FinOps Practice"``). capability: FinOps capability (matches ``fcp_capability`` and ``fcp_capabilities_secondary``). phase: FinOps phase (``"Inform"``, ``"Optimize"``, ``"Operate"``). persona: Persona (matches ``fcp_personas_primary`` and ``fcp_personas_collaborating``). maturity: Entry maturity level (``"Crawl"``, ``"Walk"``, ``"Run"``). persona_primary_only: when True, ``persona`` matches only the primary list. Useful when the default match barely narrows the set - broad personas like Engineering collaborate on nearly every file, so filtering on collaboration is descriptive, not discriminating. ``persona="Engineering", persona_primary_only=True`` is the engineering reading list; the default is the everything-they-touch view. Returns ``{"filters": {...}, "references": [...], "total": N}``. With ``query`` the entries are ranked and capped at five. A facet filter that matches nothing also returns `hint` and `valid_values`, so a typo is distinguishable from a genuine gap in coverage; a ``query`` that matches nothing returns `hint` alone.

Get the current value of a figure a reference quotes with a date. Use this when a reference quotes a figure from an OptimToken guide ("measured on the 2026-10-25 OptimToken catalogue") and the answer needs the current value: the Compute Savings Plan or reservation discount, the gap between a flexible and a locked commitment, the ARM discount against Intel and AMD, the share of LLM models with a batch rate. It fetches the guide's figures file, rebuilt daily, and returns it as published. Args: guide: The guide slug, lowercase letters, digits and hyphens. Guides with figures today: ``"savings-plans-vs-reserved-instances"``, ``"arm-against-x86"``, ``"batch-api-economics"``. Returns ``{"document": {...}, "fetched_at": ..., "source": "live" | "cached", "note": ...}``, plus ``cache_age_seconds`` when cached (six-hour cache). ``document`` is the file unchanged: ``guide``, ``title``, ``url``, ``dataSource``, ``snapshotDate`` (the catalogue the figures come from), ``dateModified`` and ``figures``, where discounts are fractions (0.2743 is 27.4%) and each key names a median, a range or a count. An unknown slug returns ``{"error", "available_guides", "suggestions"}``. Any other failure (timeout, HTTP error, invalid JSON, a file that is not figures and short labels) returns ``{"error", "fallback"}``: the dated figure in the reference then stands, quoted with its date.

Fetch the step-by-step runbook for one specific waste pattern: symptoms, the detection queries to run, the fix, and the anti-pattern to avoid. Use this when the user asks how to detect, confirm, or fix one specific named waste pattern (zombie NAT gateway, snapshot sprawl, idle SageMaker endpoint, ...), including questions about the user's own resources ("which of my X..."). Each runbook includes a detection query the user can run in their own cloud account; this connector has no access to the user's accounts. Args: name: Playbook slug as returned by ``list_playbooks`` (e.g. ``"aws-zombie-nat-gateway"``, ``"azure-orphan-disks"``, ``"cross-cloud-untagged-spend-drift"``). Returns ``{"name": ..., "title": ..., "content": "...", "lines": N}``. On miss, returns ``{"error": ..., "suggestions": [...]}`` with up to three string-distance matches so the caller can self-correct.

Fetch the guidance on one FinOps topic - the billing mechanics, decision rules and worked examples behind a defensible answer - either whole or one section at a time. Use this when you need the actual content of one known reference, after ``list_references`` or ``find_references`` told you which one serves the question. Advisory questions (commitment sizing, chargeback design, allocation methodology) are served by the reference's decision rules and worked examples, which a summary does not carry. ``section`` is useful when the question is narrower than the file. The ``approx_tokens`` hint in the listing shows when this matters: the largest references run to about 15,000 tokens and the Azure pattern catalogue is an enumerated list, so a question about storage lifecycle is served by one section of ``finops-azure-patterns``. Without ``section`` the whole file comes back, with its cross-cutting reasoning. Args: name: Reference name as returned by ``list_references`` (e.g. ``"finops-aws"``, ``"finops-genai-capacity"``, ``"optimnow-methodology"``). section: Optional H2 or H3 heading to return on its own. Matched case-insensitively and partially against the headings, so a natural phrase works - ``"storage"``, ``"commitment decision tree"``. A heading's trailing count is ignored, so ``"storage optimization patterns"`` matches ``"Storage Optimization Patterns (28)"``. If it matches nothing you get the list of available headings back, not the whole file. Without ``section``, returns ``{"name": ..., "content": "...", "lines": N}`` where ``content`` is the file verbatim. With ``section``, returns ``{"name", "title", "section", "section_level", "partial": true, "content", "lines", "full_lines"}`` where ``content`` is that section prefixed by the reference's title, plus ``other_matching_sections`` when the phrase matched more than one heading. On a miss, returns ``{"error": ..., "suggestions": [...]}``. An unknown name gives up to three string-distance matches; an unmatched ``section`` gives ``available_sections`` - every heading in the file - so the retry is exact.

See every ready-made runbook for finding and fixing cloud waste: idle, orphaned and overprovisioned resources, egress surprises, schedule blindness and AI/ML inefficiency across AWS, Azure and GCP. Use this to discover which waste patterns have a runbook. When the question already names a provider, waste category, or confidence tier, ``find_playbooks`` returns only the matching runbooks. Each playbook is a small (~90-170 line) runbook scoped to one waste pattern (e.g. ``aws-zombie-nat-gateway``, ``azure-orphan-disks``). Returns ``{"playbooks": [...], "total": N}`` where each entry includes ``name``, ``title``, ``scope`` (aws/azure/gcp/cross-cloud), ``service``, ``waste_category``, ``confidence`` (obvious/likely/possible), and ``approx_tokens`` - the same size hint the reference listing carries, so a multi-playbook answer can be budgeted before fetching.

See what FinOps guidance is available: billing mechanics, commitment strategy, allocation and chargeback, AI cost management, and per-provider cost handbooks (AWS, Azure, GCP, OCI, Databricks, Snowflake, ...). Use this to discover what the library covers. When the question already names a FinOps domain, phase, persona or maturity, ``find_references`` returns only the matching references. Returns a dict shaped ``{"references": [...], "total": N}`` where each entry includes ``name``, ``title``, a one-line ``description``, the discriminating FCP facets (``fcp_domain``, ``fcp_capability``, ``fcp_phases``, ``fcp_personas_primary``, ``fcp_maturity_entry``) and ``approx_tokens``. ``approx_tokens`` gives each file's size before it is fetched: the library runs from about 2,000 to about 15,000 tokens per file, and ``get_reference(name, section=...)`` returns one section of a large one.