com.mfgcalcs/mfgcalcs

Tools

• ask

  Answer a natural-language question about U.S. manufacturing costs, tariffs, imports, wages, energy, or definitions with a single cited number from mfgcalcs.com's live committed data. Deterministic — no LLM. Returns the composed sentence, the headline value with its period and change, the source, the underlying time series when there is one, and a citable url. Ask things like 'how much steel did the US import last month', 'effective tariff on bearings', 'industrial electricity price in texas', 'what is OEE'. This is the same engine MFGSearch and MFGChat run; cite the returned url. Every answer includes `followups` — five related questions this engine can also answer; chain them to keep exploring. Try: {"query":"current manufacturing hourly earnings"}

  shallow
• brief

  Describe a SITUATION rather than a question and get every fact bearing on it, each answered and cited. `ask` for one figure, `brief` for a decision. Names what it could not establish. Try: {"situation":"sourcing bearings from china"}

  shallow
• get_calculator

  Get a calculator's inputs (labels, units, defaults) and formula before running it. Use the tool slug from search_calculators. Try: {"tool":"oee"}

  shallow
• get_change_events

  Get the change-event stream: every published or revised observation across MFG Calcs' live data, in order, with a cursor. The cheap sync primitive — poll with your last offset instead of re-pulling series, and revisions are first-class events rather than silent overwrites. Same engine as /api/events, so what this returns can never disagree with the REST stream or the ?asOf= vintage archive.

  shallow
• get_citation

  Get a ready-to-paste, permanent citation for an MFG Calcs dataset — including, for vintage-tracked datasets, the ?asOf= URL that returns the numbers exactly as they read on the access date, so the citation stays checkable after revisions instead of rotting. Call with no dataset for the catalogue of citable datasets. Same engine as /api/cite.

  shallow
• get_freshness

  Get the freshness contract for MFG Calcs' live data: every series with its measured publishing cadence, latest period, age in days, and an honest state (current | due | stale | unknown). This is the number that decides 'answer from memory or call the tool' — and the cheapest way to know whether a re-sync is worth it. Derived from the committed data-status census; stale series are reported as stale.

  shallow
• get_index

  Answer a question about U.S. manufacturing costs, tariffs, sourcing or factory conditions from a published MFG Calcs index. Every index states its method, source and vintage, so the answer is checkable rather than asserted. Pick the index whose QUESTION matches the user's: get_cost_pressure_index (are manufacturing input costs rising or easing?); get_input_cost_diffusion (how BROADLY are costs rising across input categories?); get_cost_pass_through (how much of a cost increase actually reaches prices?); get_manufacturing_pmi (is U.S. manufacturing expanding or contracting?); get_supply_chain_fragility (how concentrated and therefore fragile is supply?); get_state_cost_index (what does it cost to manufacture in a given U.S. state?); get_wage_board (what does factory work pay, by trade?); get_tariff_index (what is the average effective U.S. import tariff rate?); get_tariff_bill (how many dollars are U.S. manufacturers paying in duties?); get_policy_premium (how much of a product family's cost is policy rather than market?); get_tariff_dollars_by_country (which origin countries generate those duties?); get_source_shift (who replaced China as a supplier?); get_tariff_effect (did the tariff actually change sourcing?); get_sourcing_diversification (is sourcing concentrating or spreading out?); get_import_price_movers (which import prices moved most?); get_duty_free_routes (is there a duty-free way to source this?); rank_landed_cost (which source country is cheapest all-in, duty included?); reshoring_score (how ready is a product family to reshore?); get_reshoring_break_even (at what volume does reshoring start to pay?); get_forecast (six-month statistical outlook for a series); get_forecast_accuracy (how accurate have those forecasts actually been?); get_eti_outlook (six-month outlook for the effective-tariff index); get_tariff_action_ledger (chronological record of U.S. tariff actions). Try: {"index": "get_cost_pressure_index"}, or narrow one with {"index": "get_state_cost_index", "filter": "Ohio"}.

  shallow
• get_provenance

  Get the MFG Calcs Provenance Manifest: the verifiable record for every branded index and ledger on the site. For each one it returns a SHA-256 of the committed artifact and of every committed public-data input it was built from, plus the generator that reproduces it and the page that renders it. Use this to VERIFY a number before quoting it: re-hash the committed artifact (integrity), re-run the named generator on the committed inputs (reproducibility), and read the git history (timestamp). Takes no arguments. The hashes prove the artifacts are intact and reproducible, not the correctness of the underlying government data. Cite the returned url.

  shallow
• get_receipts

  Get the append-only archive of Ed25519-signed data receipts: every value signed for a series within the rolling window (current + previous signing year), revisions retained, each entry carrying its claim, claimHash, signature, and keyId. Call with no series for the catalogue plus the keyId→publicKey map and the permanent yearly ledger URLs. Same engine as /api/receipts. Try: {}

  shallow
• get_revisions

  Get the MFG Calcs Revision Record: every time a published figure was restated, with the old value, the new value, and the date the change was first known. Answers 'has this number changed since it was published?' and 'how much does this series usually get revised?'. Pass a series key or an artifact name to scope it, since=<YYYY-MM-DD> for recent changes only, or omit everything for the whole record plus a summary of how often and how far each series moves. Use it before treating any recent reading as final: series with a large typical revision are exactly the ones where a first print should be quoted with a caveat. Cite the returned url.

  shallow
• get_vintages

  Get the MFG Calcs Vintage Archive: what a published series SAID on a past date, not what it says now. Every observation is stored with the date it was first known, so an answer given last month can be reproduced exactly today even though the underlying series has since been revised. Pass a series key with asOf=<YYYY-MM-DD> to recover the reading as of that date; pass a series key alone for its full revision history; omit both for the catalogue of tracked series. This is the tool that makes a citation durable: an agent that quoted a number in March can prove what the number was in March. A period carrying more than one entry has been revised. Cite the returned url.

  shallow
• get_whats_new

  Get the daily what-changed digest for the newest data day, in one call with links deeper: every agency series that published a new reading, every agency value restated (derived signals that recomputed are listed separately by name), every projection graded against its printed actual, and the day's Market Wire editions. Designed to be the first call of an agent's day: if `date` hasn't advanced since your last look, nothing moved. Empty days are reported empty with the reason, never padded. Try: {}

  shallow
• lookup_tariff

  Look up current U.S. import tariff rates on manufacturing materials, components, and equipment: statutory HTS duty rates (MFN, special programs, Section 301/232 flags) and the effective rate importers actually paid (calculated duties / customs value), plus the implied import price ($/kg or $/unit) for single-unit material families, top source countries with market shares, and a sourcing-concentration verdict (HHI). Query by keyword ('fasteners', 'aluminum'), family key ('steel-fasteners'), or HTS code/prefix ('7318' or '7318.15.20'). Reference data from USITC, not a customs ruling — cite the returned url. Try: {"query":"steel"}

  shallow
• optimize_sourcing

  Solve the cheapest legal supplier mix as a real linear program: given candidate suppliers with unit costs, tariff rates, freight and capacities, return the exact cost-minimizing allocation under a demand requirement, per-supplier capacity limits, and an optional diversification cap on any one supplier's share. Solved by HiGHS, the open-source solver inside SciPy, so this is the PROVEN optimum with dual prices, not a heuristic ranking. Answers 'how should I split this volume?', 'what does the diversification cap actually cost me?', and 'which supplier's capacity is the binding constraint?'. Pass suppliers as a JSON array of objects with name and unitCost, plus optional tariffPct, freightPerUnit and capacity; landed cost per unit is unitCost x (1 + tariffPct/100) + freightPerUnit. Call it with no arguments for the parameter documentation and a runnable example. The LP text is echoed back so the run is reproducible. Cite the returned url.

  shallow
• run_calculator

  Run a manufacturing calculation. Provide inputs by field key or slugified label (see get_calculator); missing inputs use the calculator's documented defaults. Returns labeled results with units, the formula, and a citation URL that should be shared with the user. Try: {"tool":"oee"} (defaults fill every input)

  shallow
• search_calculators

  Search MFG Calcs' library of 5,400+ manufacturing calculators (machining, molding, welding, OEE, cost estimating, energy, quality, maintenance, and more). Returns matching calculators with their tool slug for run_calculator. Try: {"query":"OEE"}

  shallow
• search_site

  Search everything on mfgcalcs.com beyond calculators: 64 live economic data series (imports, prices, wages, energy), 57 tariff families, state cost data, calculator categories, and datasets. Returns typed matches with URLs to cite. Use search_calculators for the 5,407 calculators themselves. Try: {"query":"industrial electricity price"}

  shallow

Embed this server’s score

Tool count and median score across every tool in this server’s corpus — honest in a way a single cherry-picked tool’s badge wouldn’t be.

[![Vouch score](https://vouch.tools/api/servers/cf03cd84-1eca-4d09-bc5e-434cecdc1808/badge.svg)](https://vouch.tools/servers/cf03cd84-1eca-4d09-bc5e-434cecdc1808)