MCP.Market

Finops Framework MCP server

by aaronmsoto·io.github.aaronmsoto/finops-framework-mcp·v0.2.0
No reviews yet

Unofficial MCP server for the FinOps Framework: phases, domains, capabilities, maturity, KPIs.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
New

0 stars0 downloads/wk

Reviews

Write one

Nobody has reviewed Finops Framework yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Finops Framework tools (12)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • assess_maturity_path

    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.

  • get_actions

    EXPERIMENTAL (FINOPS_MCP_EXPERIMENTAL): The discrete items parsed from a capability's Crawl/Walk/Run maturity assessment. IMPORTANT: these are assessment CHARACTERISTICS (rubric states an assessor checks for), not official to-do steps — an unofficial parsing of official prose (official:false). At 'pre-crawl' (an unofficial extension level) there is no official content; the tool returns the extensi

  • get_capability

    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 doc

  • get_changelog

    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.

  • get_entity

    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.

  • get_framework_info

    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.

  • get_kpis

    Full KPI records: description, formula + candidate data sources (present for the … 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 t

  • get_maturity_assessment

    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.

  • get_maturity_model
  • list_capabilities

    All … 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.

  • map_personas

    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

  • search_framework

    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

Public scan report

scanner v0.1.10 · 2026-10-26 · same rubric, same numbers if you re-run it

no findings
  • Code scan71 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Finops Framework compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 95% of 48,255 servers
Tools
12
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 12 read

Install Finops Framework in Claude Code, Cursor or VS Code

Runs npx -y finops-framework-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add finops-framework-mcp -- npx -y finops-framework-mcp
Add to Cursor

What the publisher says

From the Finops Framework repository's README, as published. We do not edit it. Read it on GitHub

finops-framework-mcp

Three unofficial MCP servers that give AI assistants a structured, sourced interface to published FinOps and AI-cost guidance, so an assistant answers with the publishers' actual text and formulas instead of improvising:

All three are read-only (an agent can read guidance, never change your practice or data) and offline once installed (no network access at runtime, no telemetry). Use any one on its own; together they cover what good looks like, which billing columns prove it, and what drives AI token cost.

Start here: the usage guide

aaronmsoto.github.io/finops-framework-mcp is a free, no-install walkthrough written for FinOps practitioners as much as engineers. It explains what each server does, connects them to Claude in a couple of minutes, and works through five examples, from a showback report to whether prompt caching is paying off. Every number and quote in it comes from a real run of these servers. See Documentation for the page list.

Why this exists

Ask an AI assistant "how mature is our Allocation practice?", "which FOCUS columns feed Effective Savings Rate?" or "is our prompt caching paying off?" without these servers, and it will happily improvise a plausible answer. With them, every response is the publisher's own text and formulas, structured for an assistant to read, with the source URL and license attached.

Anything a server had to work out itself is labeled, never passed off as published guidance:

cross-version diff are marked UNOFFICIAL (official: false).

  • The FOCUS server's KPI-to-column mapping, computed KPI values and

answer, because most Tokenomics Foundation guidance is a working draft or release candidate. Its curated crosswalk is unofficial and only appears with FINOPSMCPEXPERIMENTAL=1.

  • The tokenomics server states each source's publication status on every

relationships between capabilities, no maturity levels beyond the Foundation's Crawl/Walk/Run.

  • The framework server is official-only out of the box: no invented

Quickstart

All three are on npm, so there is nothing to clone or build. Each package ships its own data and runs offline. Node >= 22 is the only requirement.

npx -y finops-framework-mcp
npx -y finops-focus-mcp
npx -y tokenomics-overview-mcp

(-y skips npx's first-run install prompt, which can hang non-interactive MCP clients. Pin a version with, for example, npx -y finops-focus-mcp@0.2.)

Claude Code:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Finops Framework: common questions

Is Finops Framework MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Finops Framework safety report
How do I install Finops Framework?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Finops Framework need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Finops Framework maintained?
The last commit was 15 days ago (2026-10-20). The latest release is v0.2.0.
How does Finops Framework compare with other MCP servers?
safety score 92/100 (higher than 95% of 48,255 servers); tools 12 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from aaronmsoto →