{
  "markdown": "# freight-pulse 🚢\n\n**Ocean & multimodal freight intelligence suite for AI agents.** One MCP server that answers\n*any* shipping question an importer, CFO, or supply-chain agent actually asks — from\n*\"what's the spot rate Shanghai → LA?\"* to *\"what's my total landed cost with duty?\"* to\n*\"should I book this lane now or wait?\"* — across **47 tools** covering rates, total landed\ncost, transit reliability, customs, risk, emissions, and a unified **ship decision**.\n\n> Give it a lane, an HS code, a value — get back **one trustworthy, cross-validated answer**\n> with a confidence read, not one vendor's quote. The rate engine, port normalization,\n> customs logic, and the accumulating per-lane history all run **server-side** (the moat);\n> the npm package is a thin client.\n\n**Hosted endpoint:** `https://freight-pulse-mcp.vercel.app/mcp` · streamable-HTTP, no signup for the free tier.\n\n---\n\n## Why an agent picks this\n\nA single freight API returns **one vendor's number** with no second opinion and stops at the\nrate. freight-pulse goes the whole distance an importer needs:\n\n- **Cross-validated rates.** Reads Drewry's World Container Index (WCI) and the Freightos\n  Baltic Index (FBX) server-side (plus your own SeaRates key if you supply one) and reconciles\n  them into **one normalized USD figure** with a **confidence score** (do the sources agree?)\n  and a market direction (rising / falling / stable).\n- **The whole decision, not just the price.** Landed cost with HS-code duty, all-in door-to-door,\n  transit time + reliability (p90), air-vs-ocean trade-off, customs, risk, CO₂ — folded into a\n  single **`ship_decision`** verdict: *BOOK NOW / WAIT / SWITCH MODE*.\n- **Its own accumulating history.** Every lane queried is cached with a timestamp; trend tools\n  serve a weeks-long normalized series no single index hands an agent for free.\n- **Public, non-sensitive inputs.** Ports, HS codes, declared values — nothing secret. Safe for\n  an agent to call without handing over credentials.\n\n---\n\n## Worked example — Shanghai → Los Angeles, 40ft, $180k of cargo\n\n```\n💲 get_spot_rate     → $5,442 / 40ft · confidence 🟢 80/100 · cross-validated from Drewry + FBX (spread 11%)\n🧾 get_all_in_rate   → $6,910 all-in (BAF, THC, doc, ISF, drayage folded in)\n📦 get_landed_cost   → $193,180 delivered  (rate + 3.4% duty on HS 8516 + MPF/HMF + insurance)\n🚢 ship_decision     → BOOK NOW  ·  rate stable-to-rising, equipment available, transit p90 within SLA\n```\n\nOne agent call chain, one verdict. That's the difference between a freight API and a freight *agent*.\n\n---\n\n## What's inside — 47 tools\n\n| Area | Tools |\n|---|---|\n| **Rates & trend** | `get_spot_rate` (FREE), `get_lane_trend`, `get_all_in_rate`, `rate_benchmark` (am I overpaying?) |\n| **Total cost** | `get_landed_cost`, `total_cost_ownership`, `customs_valuation`, `customs_optimization` |\n| **Decision** | `ship_decision`, `simulate_scenario`, `compare_modes` (air vs ocean), `sourcing_analysis` (China+1 / nearshoring) |\n| **Transit & risk** | `get_port_intel` (congestion), `lane_risk_index`, `disruption`, `contingency_plan`, `get_scorecard` |\n| **Procurement** | `procurement_strategy`, `build_tender`, `evaluate_bids`, `select_provider` (forwarder/3PL), `record_performance` |\n| **Customs & docs** | `required_documents`, `incoterm_responsibility`, `qualify_fta_origin`, `export_compliance`, `check_lc_documents` |\n| **Carriers & equipment** | `carrier_recommendation`, `equipment_availability`, `booking_strategy`, `appointment_plan`, `dnd_strategy` (demurrage & detention) |\n| **Inland & load** | `door_to_door`, `load_plan`, `pallet_plan`, `optimize_network`, `cold_chain` |\n| **Finance & risk** | `payment_terms`, `fx_exposure`, `insurance_recommendation`, `inventory_optimization` |\n| **Sustainability** | `carbon_footprint` (GLEC/ISO 14083), `decarbonization_roadmap`, `reverse_logistics` |\n| **Monitoring** | `create_watch`, `check_watches`, `market_report`, `special_cargo` |\n\n`get_spot_rate` is **free** (the hook). The deep analytical tools are **premium**.\n\n---\n\n## Quickstart (MCP)\n\n```jsonc\n{\n  \"mcpServers\": {\n    \"freight-pulse\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"freight-pulse-mcp\"],\n      \"env\": {\n        // optional: unlock premium tools with a prepaid key\n        \"FREIGHT_PULSE_KEY\": \"fp_…\",\n        // optional: your own SeaRates key — cross-validated as a THIRD source, RAISES confidence\n        \"SEARATES_API_KEY\": \"…\"\n      }\n    }\n  }\n}\n```\n\nOr connect over HTTP at `POST https://freight-pulse-mcp.vercel.app/mcp` (streamable).\n\n---\n\n## Free vs Pro\n\n| | Free | Pro |\n|---|---|---|\n| `get_spot_rate` (cross-validated rate + confidence + direction) | ✅ | ✅ |\n| All 40+ analytical tools (landed cost, ship_decision, customs, risk, trend, …) | upsell preview | ✅ full result |\n| Accumulating per-lane trend history | — | ✅ |\n| Pay how | — | 🪙 **x402 (USDC on Base)** per call — agents pay automatically, no signup · or 💳 **card** via Stripe checkout for a prepaid key |\n\nTwo ways to pay a premium call:\n\n- 🪙 **x402 (USDC on Base)** — an x402-aware agent pays per call automatically, zero signup.\n- 💳 **Card (Stripe)** — buy a prepaid API key, send it as `Authorization: Bearer <key>`\n  (or set `FREIGHT_PULSE_KEY`).\n\n---\n\n## On the data\n\nfreight-pulse is **indicative market intelligence** cross-validated from public freight indices\nand customs references — not a carrier quote or a booking. Always verify with your forwarder\nbefore committing. Drewry WCI and Freightos FBX publish weekly assessments; the optional SeaRates\nsource is bring-your-own-key (it only raises confidence, never required).\n\nThe analysis engine — index fetching, port/HS normalization, cross-validation, the confidence\nmodel, customs/duty logic, and the per-lane history cache — runs **server-side**. The npm package\nis a thin client that forwards to the hosted service.\n\nMIT · [github.com/Baneado98/freight-pulse](https://github.com/Baneado98/freight-pulse) · Hosted at `freight-pulse-mcp.vercel.app`\n",
  "bytes": 5989,
  "sha": "6e1ee6062d84d83dcdad3b16060f3d8a1f4bbab8ff6e2232e005098c26482fa6",
  "repo_slug": "baneado98/freight-pulse",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_baneado98_freight_pulse_60eb2381/readme"
}