io.github.aaronmsoto/tokenomics-overview-mcp

What it mainly works on, as our AI model read its tool descriptions: nothing outside itself: it only answers questions.

None of its 20 tools are described as changing anything.

• get_tokenomics_inforeads or searches

  “Start here.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  Takes no inputs.

• list_documentson 48 other serversreads or searches

  “Every ingested tokeneconomics.com document with kind (docs/project/paper/insight), publication status, and section ids for get_document.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input

  • kindstring
• get_documenton 67 other serversreads or searches

  “Canonical markdown of one Tokenomics Foundation document, prefixed with its publication status and followed by CC BY attribution.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  2 inputs, 1 required

  • documentstringrequired“Document slug, e.g.”
  • sectionstring“Section id, e.g.”
• list_layerson 15 other serversreads or searches

  “The seven layers (L0 Energy … L5 AI access and control, the routing/gateway layer … L6 Demand and entry points) with the published summary: whether each moves the Big-T multiplier, its key metric, an…”

  Publisher declares: read-only yes · idempotent yes · open-world no

  Takes no inputs.

• get_layeron 2 other serversreads or searches

  “One layer of the Seven-Layer Stack: description, components, published tooling table, and the levers that sit at it.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input, 1 required

  • layerstringrequired“e.g.”
• get_bigt_notationreads or searches

  “Big-T notation, 'Big-O for AI consumption': T(n · k · a) = requests × model calls per request × agent depth, and the six-class complexity ladder from T(1) to T(∞), each with its published fix.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  Takes no inputs.

• get_bigt_classreads or searches

  “One rung of the Big-T ladder: what puts a workload in it, the published fix, the stack layers whose levers move it, and the levers tagged with it.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input, 1 required

  • classstringrequired“e.g.”
• list_leversreads or searches

  “Optimization levers as the Foundation publishes them: the stack's primary levers per layer (caching, batching, right-sizing, quantization, complexity routing, budgets, agent caps…), Big-T's five leve…”

  Publisher declares: read-only yes · idempotent yes · open-world no

  6 inputs

  • layerinteger
  • bigt_classstring“e.g.”
  • kindstring
  • documentstring
  • limitinteger
  • cursorstring
• get_leverreads or searches

  “Full record for one optimization lever, with provenance and status.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input, 1 required

  • leverstringrequired
• list_metricson 19 other serversreads or searches

  “The Foundation's reference metrics with their published formulas: Cache Hit Rate, Cache Cost Efficiency and uncached equivalent cost (cache explainer), net benefit and risk expected loss (value class…”

  Publisher declares: read-only yes · idempotent yes · open-world no

  Takes no inputs.

• get_metricon 9 other serversreads or searches

  “One metric's published formula, definition, inputs, 'what good looks like' targets, and its cross-links to the FinOps Framework / FOCUS servers.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  1 input, 1 required

  • metricstringrequired
• calculate_cache_metricscalculates or converts

  “Applies the cache explainer's published formulas to YOUR token counts.”

  Publisher declares: read-only yes · idempotent yes · open-world no

  7 inputs, 3 required

  • cache_read_tokensnumberrequired
  • cache_write_tokensnumberrequired
  • uncached_input_tokensnumberrequired
  • base_input_price_per_mtoknumber“Base (uncached) input price per million tokens”
  • cache_read_multipliernumber“Cache read price as a multiple of base input, e.g.”
  • cache_write_multipliernumber“Cache write price as a multiple of base input, e.g.”
  • actual_prompt_costnumber“Actual billed prompt (input-side) cost, if known”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.