Skip to main content
Glama
265,986 tools. Last updated 2026-07-06 21:16

"namespace:io.github.LLM-Pulse" matching MCP tools:

  • Run audio analysis on a public audio URL. Requires estimate_cost to be called first (job_estimate_id). Requires PULSE_API_KEY. Before calling, you MUST confirm with the user that they have a lawful basis to submit this audio for analysis. For a user-requested folder, project, playlist, or batch, one confirmation can cover every track in that scope. Returns job_id — poll get_job_status for results.
    Connector
  • Return a canonical definition for a primitive Eurorack / synthesis concept and its relations to other concepts in the corpus. Use this for VOCABULARY questions, not module questions — when the user is asking what a term means or how two terms relate, not which modules implement it. Typical shapes: - "Is four-quadrant mult the same as through-zero AM?" → lookup_concept("four-quadrant mult") - "What's the difference between a gate and a trigger?" → lookup_concept("gate") - "Modular signal level vs line level — when does it matter?" → lookup_concept("modular signal level") - "Are clock dividers just pulse counters?" → lookup_concept("clock divider") - "Are polyphonic patch cables TRRRRRS?" → lookup_concept("polyphonic cable") Lookup is case-insensitive across three axes, tried in order: the canonical id ("through-zero-fm"), the canonical label ("Through-Zero FM (TZFM)"), and any registered alias ("tzfm", "through zero fm"). Spaces and hyphens are matched literally; the lookup does NOT normalize whitespace beyond lowercasing. If the term doesn't match anything, the response includes up to 5 substring-matched suggestions. Args: - name (string, required, min length 2): the term to look up. Examples: "AM", "ring mod", "four-quadrant mult", "TZFM", "clock divider", "gate", "trigger". Returns: { "concept": { "id": "amplitude-modulation", "label": "Amplitude Modulation (AM)", "description": "A multiplication of two signals: the carrier...", "aliases": ["am", "amplitude modulation", "amplitude mod"], "related_concepts": [ { "related_concept_id": "ring-modulation", "related_concept_label": "Ring Modulation (RM)", "relation_kind": "commonly_confused_with", "note": "AM with a unipolar modulator preserves the carrier..." }, ... ], "source_id": null, "citation_url": "https://learningmodular.com/glossary/...", "citation_quote": "Amplitude modulation is when..." } | null, "_meta": { "query": "<the name argument verbatim>", "matched_via": "id" | "label" | "alias" | "none", "concept_suggestions": [ { "id": "...", "label": "...", "matched_via": "alias", "matched_text": "..." } ], "feedback_hint": "...?" } } Relation kinds: - "related_to" — see-also link (default; symmetric in spirit). - "subtype_of" — X is a specific case of Y (RM ⊂ AM, TZFM ⊂ linear FM). - "inverse_of" — X is the opposite of Y (clock-divider ↔ clock-multiplier). - "commonly_confused_with" — they're distinct, but people conflate them (gate vs trigger, AM vs RM, modular level vs line level). When to cite: every concept carries either source_id or citation_url + citation_quote. Surface the citation when the answer affects a decision (e.g. "the corpus cites learningmodular.com — TRS cables are physically the same connector whether carrying balanced mono or unbalanced stereo; only the destination determines the role"). When the result is null and concept_suggestions are provided, present 2–3 closest matches to the user. If none look right, the corpus genuinely doesn't carry that concept — call report_gap with kind="missing_field" and tool_name="lookup_concept" naming the term and its expected definition.
    Connector
  • Check whether the shipper can even GET A CONTAINER on a lane — and what the equipment imbalance costs — BEFORE pricing the move. The rate tools assume a box exists; this answers the constraint that often binds first: in a deficit origin you can have a rate and a sailing and still not secure a box. Returns a 0-100 AVAILABILITY INDEX for the empty box at the origin and a SHORTAGE-RISK score, driven by the structural EQUIPMENT IMBALANCE of container trade: trade is directional, so empties PILE UP at net-importer ports (LA/Long Beach, Rotterdam, Hamburg) and run SHORT at net-exporter hubs (north/central China, Vietnam) — carriers must reposition empties back against the loaded headhaul. It models the balance per TYPE: 40HC (the deep-sea workhorse) is the tightest dry type in a crunch, 20DV is structurally easier to source (the classic alternative), and REEFER is a separate, far scarcer, plug-limited pool. It overlays the SEASONAL swing on the real lunar calendar: the acute PRE-CHINESE-NEW-YEAR crunch (every exporter loads before the factory shutdown — equipment, not space, becomes the binding constraint), the POST-CNY glut (the empties that surged out sit stranded at destinations while China demand collapses), Golden-Week front-loading, and peak-season tightening — evaluated for YOUR ship date. It prices the EQUIPMENT-IMBALANCE SURCHARGE (EIS) and reposition cost the deficit imposes, plus the soft +% it pushes onto the effective booked rate, and lists the reposition INCENTIVES (triangulation/street-turn, fast empty return) that relieve it. When the requested box is short it proposes ALTERNATIVES — split a scarce 40HC into 2×20DV, shift the ship window out of the crunch, triangulate an import empty, or book a mega-fleet carrier (Maersk/MSC/CMA CGM) whose deep own-box pool and local depots ease the SAME deficit (a thin niche line is more exposed). Pass a carrier to refine the numbers. The shortage risk also feeds the book-now timing — a worsening crunch means anticipate and lock equipment early. Everything is a MODELED structural + seasonal profile expressed as honest bands — NOT a live depot inventory; we never claim a specific box count is available at a depot today (regla 7). PREMIUM: pay per call with x402 (USDC on Base) or set a prepaid key (FREIGHT_PULSE_KEY). Same UN/LOCODE port normalization as get_spot_rate.
    Connector
  • Decide the TRANSPORT MODE for a shipment — OCEAN vs AIR vs SEA-AIR — on TOTAL economic cost, not just freight. The other tools price the ocean move; this one answers the importer's prior question: should these goods even go by sea? It costs all three modes and recommends the economically optimal one. Air is priced correctly on the IATA CHARGEABLE WEIGHT = max(actual gross weight, volumetric weight at 167 kg/m³) with an air fuel (FSC) + security (SSC) + handling stack — so bulky-but-light cargo is properly penalised (the lever a naïve 'air is just faster' estimate misses). Sea-air is modeled via the real hubs (Asia→Europe via Dubai/Jebel Ali, Asia→US-East via a US-West gateway): a cheap ocean leg to the hub + a short air final leg. The recommendation runs a real DECISION MODEL: cost of CAPITAL tied up in transit (value × annual rate × days), a p90 safety-stock HOLDING cost from each mode's variability, and — if you pass a deadline — an EXPECTED STOCKOUT cost from the probability the mode arrives late. So for high-value goods (or a tight deadline) air/sea-air can win even though the freight is far dearer, while for cheap goods ocean's much lower freight dominates. Returns the full ocean/air/sea-air table (freight, p50/p90 transit, capital, holding, stockout, total economic cost) + the recommended mode + the trade-off math. Every figure is modeled and tagged; air rates are volatile so they are honest BANDS, not a quote. PREMIUM: pay per call with x402 (USDC on Base) or set a prepaid key (FREIGHT_PULSE_KEY). Same UN/LOCODE port normalization as get_spot_rate.
    Connector
  • Check whether it is LEGAL to EXPORT a given product to a destination, and whether it needs an export LICENCE — the goods-side trade-compliance question (NOT denied-party / sanctioned-person screening, which is a separate regulated process this tool does NOT perform). Pass a product description (reusing the same HS classifier as get_landed_cost) or an HS code + the lane. It classifies the goods against the DUAL-USE control lists (a modeled ECCN / EU Annex-I dual-use category: advanced electronics, encryption/information-security, sensors & lasers, navigation, aerospace, nuclear, special materials, machine tools, controlled telecom), reads the DESTINATION's embargo / restriction level (comprehensive embargo, arms/dual-use embargo, licence-required, partial, or permissive — modeled at a high level), and runs the decision tree: a dual-use good to an embargoed destination is BLOCKED; a dual-use good to a licence-required destination needs a LICENCE; an ordinary good to a permissive destination is likely PERMITTED; and anything ambiguous returns REVIEW-REQUIRED. ⚠️ THIS IS THE MOST LEGALLY SENSITIVE TOOL. The classification, the dual-use flag and the embargo list are a MODELED, SIMPLIFIED, NON-AUTHORITATIVE planning aid — NOT legal advice, NOT an official commodity classification (e.g. BIS CCATS), and NOT a current sanctions determination. Lists change; control hinges on exact technical parameters and end-use. You MUST verify with your government licensing authority (US BIS / the relevant EU member-state authority) and qualified trade-compliance counsel before exporting (regla 7). PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key. Same UN/LOCODE port normalization as get_spot_rate.
    Connector

Matching MCP Servers

Matching MCP Connectors

  • Ocean & multimodal freight intelligence: rates, landed cost, transit, customs, risk, ship decisions

  • 825 paid intelligence endpoints in one MCP server — agents pay per query via x402 USDC on Base.

  • Register a standing WATCH on a lane so freight-pulse alerts you when something changes — the feature that makes it a recurring daily tool, not a one-shot lookup. Give a lane + one or more THRESHOLDS and it persists the watch SERVER-SIDE (in our own store, per your key): 'spot-below' / 'spot-above' a USD level (buying window / cost ceiling), 'reliability-below' a score (rollover/delay risk), 'disruption' (any active disruption appears on the corridor/ports), 'book-now' (the forecast/timing engine flips to a book-now window), or 'forecast-rising' / 'forecast-falling' beyond a % move (act early / wait). It returns the watch id and the registered thresholds. Pair it with check_watches, which your agent polls (e.g. daily) to get back only the alerts that fired. Honest (regla 7): evaluated against modeled engine outputs — an alert is a signal to look, not a booking trigger. PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key.
    Connector
  • Generate a one-time Stripe payment page for users without a Pulse account. Before calling, you MUST confirm with the user that they have a lawful basis to submit this audio for analysis; for a user-requested batch/folder/project, one confirmation can cover that scope. Present the payment_url to the user as a link. Analysis begins automatically after payment. Poll get_job_status with the returned job_id.
    Connector
  • Fetch a historical time series of daily snapshots for one crypto ticker. Call this when the user asks about a ticker's recent trend, wants to chart or plot α-sentiment / α-index / α-pulse over time, asks "how has X changed over the last N days", or needs a window of data to compute averages, momentum, or volatility. Required: `ticker` — MUST be suffixed with "-USD" (e.g. "BTC-USD", "ETH-USD", "SOL-USD"). Bare symbols like "BTC" will not match. Optional: `days` (1-1000, default 30; tier may cap lower). Tier caps on `days`: free=7, alpha=365, pro=730, enterprise=1000. The `date` parameter (end-date anchor) is only honored for enterprise tier — for all other tiers it is silently ignored and the window always ends at the most recent available snapshot. This is by design to prevent back-testing on arbitrary historical periods on lower tiers. Returns: array of daily snapshots (oldest first), each with snapshot_date plus all standard AssetSnapshot fields. Response also reports tier_cap, effective_days, start_date, end_date and date_param_honored.
    Connector
  • Use this read-only tool to retrieve compact SEC CompanyFacts/XBRL materialization rows for the crypto public-company universe or a specific ticker/CIK. It returns one compact row per issuer for a materialized companyfacts source_date, including tag counts, crypto/digital-asset flags, top tags, taxonomies, evidence hashes, and fact source pointers. Parameters: source_date replays a known YYYY-MM-DD materialization slice; ticker or cik optionally narrows to one issuer; limit defaults to 25 and is capped at 250; offset paginates the universe. Behavior: read-only and idempotent; it performs no writes, has no destructive side effects, and never returns the raw facts_payload, so use fact_source_pointer plus evidence_hash for drilldown/audit. Use this for Mirror Pulse or ATLAS-7 historical joins when you need the compact issuer-level CompanyFacts inventory for all 215 crypto companies.
    Connector
  • Use this read-only structured history tool when Mirror Pulse, backtests, or agents need daily ATLAS-7 CompanyFacts-derived factor rows keyed by as_of_date. It returns point-in-time-safe rows derived from the latest CompanyFacts archive by applying only facts with filed <= as_of_date; rows are retrospective recomputations and include lookahead safety flags. Parameters: optional ticker or CIK, source_date, as_of_date_from, as_of_date_to, mode=compact|full, limit, and offset. Behavior: read-only and idempotent; it performs one HTTPS read, has no destructive side effects, does not generate Natural Language, and never executes trades, wallets, or settlement flows. Use compact mode by default for Mirror Pulse joins; use full mode only for selected audit pages because factor_payload can be larger.
    Connector
  • Fetch the most recent NIST Randomness Beacon pulse: a publicly verifiable, timestamped 512-bit random value signed by NIST, updated every 60 seconds.
    Connector
  • Get aggregated insights for a Coimbatore locality: avg price, supply count, demand pulse, livability/investment grade, highlights, watchouts, 12-month priceTrends, and strengthTags. Use when the user asks "what is X locality like" about a Coimbatore neighborhood. Out-of-scope cities return supported=false; surface the scopeMessage to the user. Always surface the disclaimer field when returning livability or investment grade.
    Connector
  • The AgentsPrice hive-mind pulse — a FREE, no-key, real-time aggregate of what agents are doing across the network right now: trending searches, the steepest live discounts found, open buy-side wants, and active marketplace listings. Real data only, never fabricated; richer the more agents use it. Use it to see demand, spot deals, or find what to list. No API key required.
    Connector
  • Run a WHAT-IF on a lane: recompute the COST and TIME impact of a structural change to the freight market, on top of freight-pulse's engines. Scenarios: 'red-sea-reopen' (Suez/Bab-el-Mandeb reopens and Asia-Europe / the Suez share of Asia-US-East services return from the Cape-of-Good-Hope diversion → shorter transit, war-risk & diversion surcharges fall — only material on Suez-exposed lanes); 'fuel-spike' (bunker VLSFO up X% → the BAF/bunker portion of the all-in rises; pass fuel_spike_pct); 'cny' (Chinese New Year front-loading: the pre-CNY rush spikes the spot rate and the equipment crunch and dips schedule reliability — material on China-origin lanes); 'tariff-change' (destination duty changes by X percentage points — e.g. a new Section-301 tranche or an FTA change — raising/lowering the landed cost while freight is UNCHANGED; pass tariff_delta_pp and value). It recomputes the affected engine outputs under the perturbed inputs it can thread (fuel proxy, ship date) and models the structural ones (the Red-Sea routing flag, a tariff delta) as explicit, transparent adjustments — never silently — and reports the baseline, the scenario and the deltas. A what-if is a MODELED counterfactual, not a prediction the event will occur (regla 7). PREMIUM: pay per call with x402 (USDC on Base) or set a prepaid key (FREIGHT_PULSE_KEY). Same UN/LOCODE port normalization as get_spot_rate.
    Connector
  • Assess SPECIAL / NON-STANDARD CARGO for a lane — dangerous goods, refrigerated (reefer), and out-of-gauge — the moves a plain 'dry box' rate model can't price or clear. DANGEROUS GOODS (IMDG): give a hazard class ('3', '2.1', 'class 9') or a commodity that classifies to one (e.g. 'paint' → Class 3 flammable liquid, 'lithium batteries' → Class 9), and it returns the IMDG hazard family, the STOWAGE category (on/under deck), the SEGREGATION requirements against any other classes you list in the same booking, the documentation burden (the shipper's Dangerous Goods Declaration + class-specific papers), the per-class DG SURCHARGE, and — the decision that matters — whether that class is ACCEPTED on a standard liner service, needs prior approval, or is commonly REFUSED (Class 1 explosives, 6.2 infectious, 7 radioactive). REEFER: give a commodity ('frozen shrimp', 'bananas', 'pharma 2-8') and it returns the carrying SETPOINT + tolerance band, the regime (frozen/chilled/pharma/ambient-controlled), the cold-chain RISK (a pharma GDP breach can total the cargo; a banana below 12°C is chilling injury), and the reefer plug + pharma cold-chain + controlled-atmosphere PREMIUMS. OUT-OF-GAUGE (OOG): give over-dimensions (length/width/height in cm + weight) or request a flat-rack/open-top, and it picks the equipment, computes how many neighbouring SLOTS the protrusion sterilises, the OOG surcharge (equipment + slots + lashing/survey), and the BREAKBULK fallback when nothing fits a box. Every figure is MODELED planning data — NOT the IMDG Code, a carrier DG acceptance ruling, or a certified declaration (regla 7). PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key. Same UN/LOCODE port normalization as get_spot_rate.
    Connector
  • Find the DUTY-SAVING levers a customs broker knows but the importer usually does not — and quantify each against your shipment's REAL landed-cost duty. Give a product (or HS code) + the lane + the FOB value + your trade FLOW (import & sell / re-export / import-components-assemble-re-export / store), and it returns, ranked by saving: DUTY DRAWBACK (US 99% recovery of duties on goods you re-export — honestly flagging that Section 301 is NOT drawback-eligible, the big China carve-out); FOREIGN-TRADE ZONE / FREE ZONE (eliminate duty on the re-exported share, defer it on the rest, inverted-tariff election); BONDED / CUSTOMS WAREHOUSE (defer the duty cash-flow until withdrawal, or avoid it on re-export); EU/UK INWARD PROCESSING (suspend duty on inputs you process & re-export) and OUTWARD PROCESSING (duty only on value added abroad); FIRST-SALE valuation (US — value on the lower factory price, cutting MFN AND 301 proportionally); and TARIFF ENGINEERING (legally reclassify to a lower-duty HS line). Each lever shows the money saved, whether it's cash-back vs cash-flow-deferral vs a rate/base cut, and the catch — plus a clearance-workflow checklist. Reuses the real landed-cost engine so the duty base, 301/232/FTA stack and import VAT are genuine. ⚠️ Aduanas are complex: every figure is MODELED, INDICATIVE planning intelligence, NOT customs/legal/tax advice — confirm eligibility and obtain binding rulings with a licensed broker (regla 7). PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key. Same UN/LOCODE port normalization as get_spot_rate.
    Connector
  • Compute the correct DUTIABLE BASE on which the duty is charged — it is NOT just the invoice. Under the WTO Customs Valuation Agreement, give the destination country + invoice price + Incoterm and it builds the TRANSACTION VALUE: it normalises the price to an FOB-origin base (stripping freight/insurance/destination/duty a CIF or DDP price already carries), then ADDS the statutory additions importers forget — ASSISTS (free tooling/moulds/design — inflate the base), royalties, SELLING commission, packing — while EXCLUDING buying commission and post-import costs, and applies the COUNTRY BASIS: CIF (EU & most — international freight+insurance IN the base) vs FOB (US — excluded). It returns the line-by-line base, the duty on the correct base vs the naive invoice (the over/under-payment), and the DEDUCTIVE (resale-back-calc) and COMPUTED (cost build-up) methods when there is no transaction value. Honest (regla 7): INDICATIVE model of the method hierarchy & adjustments; related-party tests, first-sale and assist apportionment are case-specific — NOT a customs ruling or legal advice. PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key.
    Connector
  • When and how to RESERVE space so your box isn't rolled and your cargo isn't stranded on the dock. Give the lane + ship date + criticality, and it reads the demand PRESSURE (composing the seasonality calendar — CNY / Golden Week / transpacific peak — with the equipment-crunch signal) into a band (slack → acute), then returns: the optimal BOOKING WINDOW (lead days, plus a criticality buffer, and the date to book by), the SPOT vs CONTRACT rollover probability and roll-delay days, and the GUARANTEED/PREMIUM-booking trade-off — the certain premium surcharge vs the expected rollover-delay cost of riding spot (roll prob × delay days × per-day criticality cost). It recommends spot, a guaranteed booking, or — if your committed volume justifies it — a named-account allocation. Proves: peak/CNY → book earlier + pay for the guarantee; slack market → ride spot. Honest (regla 7): INDICATIVE rollover probabilities & premiums by band (reusing the real seasonality/equipment calendars) — not a space guarantee or carrier quote. PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key.
    Connector
  • Plan the terminal APPOINTMENT and the box sequence so you don't eat demurrage & detention. US/EU terminals require a timed appointment to pick up the import container and to return the empty; miss the window and dwell climbs and D&D starts. Give the lane + ship date and it reads the destination port congestion (iter7) at arrival, derives APPOINTMENT-SLOT availability (how far out the first slot is and how likely a desired slot is missed — the real dwell driver), then returns: the OPTIMAL PICKUP WINDOW (late enough not to pre-pay storage, with a reserve for a missed slot, by-date inside your free days), the PICKUP→EMPTY-RETURN sequence (a dual transaction where the port supports it to cut detention), and the expected D&D of the plan vs sending the trucker blind, with the saving. Proves: a congested port (LA/LB at peak) → tight slot window, book earlier, dual-transaction the empty → saves $X of D&D; a fluid port → same-day slots, relaxed window, no premium. Honest (regla 7): INDICATIVE — appointment availability, slot scarcity and dual-transaction behaviour are modeled by port & congestion band, NOT a live terminal appointment feed (eModal/Voyage/TideWorks). PREMIUM: pay per call with x402 (USDC on Base) or a prepaid key.
    Connector