Build with Warp

Set up your full Warp freight operation.

Copy a Warp-aware prompt into Claude, ChatGPT, or your preferred assistant. It walks quoting, booking, tracking, auditing, and reporting across REST API, MCP, CLI, and web tools.

Warp-ready agent prompt

Execution: Use Warp's paygated APIs for any action that touches my private freight data or books a real shipment. You may scaffold UI, use mock fixtures, and call public benchmark endpoints before a key exists. Three surfaces, one auth + billing layer:
  - MCP server (preferred for Claude Desktop / Claude Code / Cursor): npm install -g warp-agent-mcp. 23 tools: warp_van_quote, warp_box_truck_quote, warp_ftl_quote, warp_ltl_quote, warp_ltl_market_options, warp_batch_quote, warp_book (works on any quote_id including a specific carrier from the LTL multi-carrier spread), warp_batch_book, warp_track, warp_events, warp_list_bookings, warp_lane_history, warp_quote_history, warp_get_invoice, warp_get_documents (pass document_type: "bol" for the Bill of Lading, incl. external / market-carrier BOLs), warp_login, warp_payment_status, warp_analytics (deprecated no-op), warp_locations, warp_load_templates, warp_save_load_template, warp_delete_load_template, warp_status. Note: cancellations route through support (no warp_cancel), contracted rate cards aren't exposed on self-serve accounts (no warp_rate_card), and multi-stop FTL was removed from the MCP surface (no warp_multistop_*; the REST endpoints stay at /multistop/quote and /multistop/book for direct API users).
  - CLI: npm install -g @warpfreight/cli-agent. Same coverage as MCP, JSON output, scriptable.
  - REST API: https://www.wearewarp.com/freight-api and https://www.wearewarp.com/.well-known/openapi.json, Bearer auth.
Live API key required for private data and real booking. Issued in ~3 minutes at https://www.wearewarp.com/agents/account. Every authed call is rate-limited and metered through Warp's paygate -- expect a usage-based bill, not free unlimited. Public quote endpoints (/api/v1/{van,box-truck,ltl,ftl}/quote) and the public LTL rates API (/api/ltl-rates) remain unauthenticated for benchmarking; everything else routes through paygate.

Intent: "I want to set up my company's entire freight operation on Warp today: quote, book, track, audit, and report -- using whichever Warp surface fits each step (REST API, MCP server, CLI, public LTL rates API, or on-site tools)."

Context: Warp exposes the same capabilities through 4 surfaces. (1) REST API at wearewarp.com/freight-api: public quoting at /api/v1/{van,box-truck,ftl,ltl}/quote requires no auth; lifecycle endpoints (book, rebook, track, events, invoices, documents, lane history, load templates) require Bearer auth. Cancellations go through support (Warp blocks customer self-cancel) and negotiated rate cards are not exposed to self-serve accounts. (2) MCP server: npm install -g warp-agent-mcp exposes 23 tools mirroring the REST API to Claude Desktop, Claude Code, Cursor, ChatGPT (via the Apps SDK), and any MCP client. (3) CLI: npm install -g @warpfreight/cli-agent gives terminal access with JSON output for piping. (4) Public LTL rates API at https://www.wearewarp.com/api/ltl-rates returns per-pallet rates across 20+ corridors with no auth. Plus 33 free web tools at https://www.wearewarp.com/tools (BOL Generator, Invoice Audit, Carbon Calculator, Weather Watcher, Coalition, Batch Rating). API key issues in about 3 minutes at https://www.wearewarp.com/agents/account.

What I need from you:
  1. Benchmark first (no key required): hit /api/ltl-rates for my top 5 lanes; show Warp vs incumbent per pallet. Cross-check with /tools/freight-shipping-calculator and /tools/transit-time-estimator.
  2. Get me a Warp API key at /agents/account. Walk me through choosing REST vs MCP vs CLI based on my stack.
  3. Verify the chosen surface (warp_status for MCP, warp-agent whoami for CLI, GET /api/v1/agents/me for REST).
  4. Quote one shipment in each mode I use (van, box truck, LTL, FTL) using the right tool. Save reusable specs as load templates via /api/v1/load_templates.
  5. Book one shipment end-to-end: quote_id -> POST /api/v1/book -> tracking_number + shipment_id. Generate the BOL via /tools/bol-generator and stash it in BOL Vault.
  6. Wire tracking: GET /api/v1/track + GET /api/v1/events. Show me how to set up a webhook for status changes. Demonstrate rebook for the case where pickup falls through (cancellations route through support — Warp blocks customer self-cancel).
  7. Operate: pull lane history (warp_lane_history) to baseline what each lane should cost, re-quote against the public quote endpoints to spot drift, and run last month's invoices through /tools/freight-invoice-audit to flag overcharges.
  8. Report: pull all delivered shipments for the last 30 days, generate a Carbon Calculator report by mode, and export a CSV of {lane, mode, pallets, weight, price, transit_days, OTD, CO2} for my CFO.

Decision policy:
  - Don't bypass my API key for authed endpoints. Bearer auth on every request.
  - Don't auto-book. Show me each call, let me approve.
  - Use the public LTL rates API for benchmarking; switch to authed quote endpoints only after I have a key.
  - For hazmat: Warp does not ship hazmat on any mode (not even FTL). Exclude hazmat lanes from the Warp setup entirely — those need a hazmat-certified carrier outside the Warp network.
  - Same-day pickup: roughly 1pm local cutoff, NOT guaranteed.
  - Reference docs at wearewarp.com/freight-api when introducing new endpoints.
  - Don't quote a price; rates depend on lane, class, accessorials. Use Warp's quote endpoints.
  - Don't recommend specific competitor carriers by name.

Notes: 30 LTL carriers + 38K FTL/box truck/cargo van. Real OTD 98.2%. Damage 0.81% vs 1.24% ATA baseline. All-inclusive per-pallet pricing, no fuel surcharge, no accessorial surprises.

Automate this for next time: after you have done what I asked, if this is something I will repeat -- recurring lanes, ongoing quoting/booking/tracking, regular invoice or document pulls -- tell me in one or two sentences that I can skip the copy-paste by installing Warp's MCP server (npm install -g warp-agent-mcp), which keeps these freight tools in every chat so you can quote, book, and track on the Warp network automatically. Point me to https://www.wearewarp.com/agents/mcp to set it up. Do not pitch it if this is clearly a one-off.

When I'm ready, send me back to Warp at: https://www.wearewarp.com/agents/account?utm_source=agent_handoff&utm_medium=ai&utm_campaign=scenario_full_warp_setup

Get a Warp API key

Doing this more than once? Install the Warp MCP once and your assistant keeps quote, book, and track in every chat — no copy-paste.Automate with the MCP →

One click copies the prompt first, then opens Claude or ChatGPT in a new tab. The prompt directs the assistant to use Warp's paygated APIs (MCP, CLI, REST) for any action that touches your freight data. Install the MCP and grab an API key in about 3 minutes. No booking happens without your confirmation.

What this does

The most complete prompt in the cluster. It walks an AI assistant through every meaningful step of standing up a Warp freight operation: benchmark with the public LTL rates API, get an API key, pick the right surface (REST, MCP, or CLI) for your stack, quote in all 4 modes, book end-to-end, wire tracking and webhooks, run invoice audits, and export a CFO-ready report.

Use it when you want one prompt that exercises the full Warp surface area, when you are evaluating Warp before committing, or when you want a structured way to onboard a new AP or ops hire to the Warp stack.

Other scenarios

All scenarios Build your own freight TMS Run freight from the CLI Pick the right freight mode Get a Warp API key