evolvedmcp.cloud

Price an abrasive-blasting job with the company rate engine: learned $/sqft rates by blast depth and surface, access factor, mobilization, 5% GST, 25% deposit — plus a full profitability check (media, labor, fuel, overhead, break-even rate, margin verdict).

Create a formal quote in the books (auto-numbered ECO-Q-MMDDYY-NN, valid 30 days) for a customer, from one or more priced lines.

Render a quote as a polished, dark-brand HTML document (Boreal Void page, Cyber Lime underline, Aurora Neon labels, diamond bullets, payment schedule with the big green total) ready to print to PDF and send.

Move a quote through its lifecycle: Draft → Sent → Accepted/Declined/Expired.

List quotes, optionally filtered by status.

Show the live rate table: base market rates by blast depth, the learned effective rates by surface (driven by real job outcomes at healthy margins), access factors, and the mobilization fee.

Record a job outcome (won/lost, quoted rate, actual cost per sqft, margin) into the pricing learning loop.

Reference a $/sqft rate against the going market band for a blast depth (and surface): below, within, or above market, with a percentile and plain-English guidance.

Show the pricing engine's learning state: winning-job samples, confidence (rises with data, falls with volatility), the suggested quote range (tightens as confidence grows), and where the learned rate sits against the market.

Run a receipt through the tiered extraction pipeline: fast model first, automatic escalation to a stronger model when confidence is low or the math does not reconcile.

Expense breakdown by category and vendor for a month (YYYY-MM, default current).

Invoice a completed job: pulls the quote lines, applies the deposit already collected, computes 5% GST and the balance due (net 14).

Render an invoice in the company's dark brand as a self-contained HTML document ready to print to PDF.

Profit & loss for a month or the whole book: revenue from paid invoices, expenses from the receipt ledger, per-job margins from recorded actuals, and the business scorecard (win rate, average $/sqft, overall margin).

Log a new lead into the sales funnel (New → Contacted → Site visit → Quoted → Won/Lost).

Move a lead through the funnel and refresh its next action.

The whole funnel at a glance: open leads by stage with next actions, quotes out with age, and jobs by dispatch status.

Book a job onto the dispatch board: date, crew, deposit status.

Close out a job with real numbers: hours, crew size, materials, fuel.

Customer book with contact details and their quotes/jobs at a glance.

Open the day's FLHA for a job before work starts.

Close the day's FLHA: every crew member signs, incident status is recorded, and the assessment becomes part of the job's permanent safety record.

The one-screen escalation from the deployed field app: a crew member found something unsafe and needs it off their hands NOW.

The safety record: FLHAs (open assessments needing sign-off, signed records, incident flags) plus hazards escalated from the field and whether they have been cleared.

The 6:30 AM owner briefing, on demand — a proactive 'here's your day / here's what needs you' rundown: the one thing not to drop, today's jobs with crews, the upcoming few days' schedule, money pulse (month revenue, expenses, receivables), deposits gating work (money in but unscheduled, or accepted work awaiting a deposit), quotes out with age, leads needing a touch, top open to-dos, low-inventory reorder alerts, the auto-raised action-item 'ball-drops', five-day blast-day weather verdicts, and system health.

Run the ball-drop catcher across the books.

Mark an action item handled.

Five-day forecast with blast-day verdicts (Good blast day / Marginal / No-go) using the company's gating thresholds: no blasting at precip ≥50%, wind >40 km/h, or highs below 3°C.

Restore the synthetic demo dataset to its seeded state (all names, numbers, and dollar figures are invented).

Everything on one screen: funnel counts, money position, open safety items, and open action items.

Stock levels across all three sections (Materials & Media, Consumables & PPE, Equipment & General) with par levels, reorder thresholds, low-stock flags, and last-paid pricing.

Book received stock: bumps on-hand, records the movement, updates last-paid cost/supplier, and appends to the price log (so the price-watch and reorder engines learn real COD pricing).

Log media/consumable usage against a job.

Everything at or below its reorder point, with suggested order quantity (back to par), preferred supplier, last-paid unit price, estimated cost, and recent burn rate so nothing runs out mid-job.

Supplier price history per product from real purchases: last price vs previous, percent change, and spike flags (≥10% increase).

One search across the whole rolodex.

Add a supplier to the rolodex with products carried and contact details.

What the company actually pays each supplier, by product: purchase history from the price log with latest unit prices — the negotiating sheet for the next order.

Add a crew member with role, certifications, and loaded hourly rate.

Active crew with roles, rates, certifications, expiring-cert flags, and current job assignments from the dispatch board.

The data spine as an operations workbook: every tab with its row count.

Read any tab as headers + rows (display values), like the production router's readTab.

Append-only write to the To-Do tab (the workbook discipline: insert, never overwrite).

The crew-facing capture path: anything from the field lands as exactly one append-only inbox row (lead, receipt note, job photo note, supplier, todo, quick thought).

Inbox rows by status — NEW rows await filing; NEEDS REVIEW rows want a human or smarter judgment.

Deterministically route NEW inbox rows to the right book: lead → Leads (+customer), todo → To-Do, supplier → Suppliers, receipt → the OCR expense pipeline, quick → keyword-sniffed or NEEDS REVIEW.

Canonicalized vendor spend: total spend, receipt count, category, first seen — with new-vendor flags.

The 3-day style audit: receipts with OCR warnings, arithmetic that does not reconcile (subtotal + GST ≠ total), future/stale dates, and missing job attribution on job-sized spends.

Draft polite-but-firm reminder messages for every unpaid invoice, escalating tone with age (gentle < 7 days, direct 7–20, final notice 21+).

Turn an invoice into an on-chain payment request on OKX X Layer TESTNET: EIP-681 payment URI, recipient, amount in test OKB (fixed synthetic FX rate), chain details, and explorer link.

Confirm settlement of a payment request.

Live read-only connectivity check against the X Layer testnet RPC: chain id and latest block.

How Evolved monetizes as an ASP: the HTTP endpoint exposes POST /mcp (free) and POST /mcp-paid (x402).

Kick off the full lead-to-paid lifecycle from one description: creates the lead and customer, prices the work with the learning engine, drafts the quote, and pauses at the human money gate (approve-quote).

Push a lifecycle forward through every stage it can reach.

Every lifecycle with stage, open gates, and full step log — the audit trail of an autonomous engagement.

Record a client's e-signature on a sent quote using its HMAC acceptance token.

Log the customer's post-job review (1–5 rating and comment) against the review request — closes the loop on the engagement and builds the reputation ledger.

A customer texts a photo; this turns it into a priced, branded draft quote.

Field crew talk, the books listen.

Answer the questions owners lose sleep over, with numbers: add a second truck (capex, added fixed cost, utilization ramp, break-even month), change rates (with price elasticity), or shock demand.

The CFO one-pager: receivables aging, customer concentration risk, monthly run-rate from the books, weather-capacity outlook (share of blastable days ahead), review reputation, and the three numbers to fix first.

Turns the books into decisions, not records.

The deterministic business brain: spend pulse vs last month, top and new vendors, inbox backlog, reorder alerts, pending on-chain settlements.

Rate an insight (Important / Not important / Done).

The audit trail: every capture, filing, receipt, payment, and voice command in reverse-chronological order.

Full snapshot of the data spine to a timestamped backup file.

Every backup snapshot on file.

The productization story in one call: re-seed the entire operations brain for a NEW company — any name, any trade, your rate card — with empty books and the full machinery intact (quoting engine, receipts pipeline, FLHA library with trade-specific hazards, digest, learning loop, on-chain invoicing).

The state of the operations-workbook spine: linked Google Sheet (if any), tab list, cell counts, credential mode, and last sync time.

Render the ENTIRE operating system — quotes, dispatch, expenses, invoices, inventory, crew, time log, photos, field notes, safety, reviews, action items, rate table, Job P&L, record log — as a CSV workbook bundle.

Spin up a REAL Google Sheets operations workbook from the current database — every collection a tab, exactly like the production company's workbook.

Attach Evolved to a Google Sheets workbook you already have (by spreadsheet id).

Push the entire current database into the linked workbook — updates every tab (adds missing ones) in the linked Google Sheet, or refreshes the CSV bundle when running credential-free.

File a before/after/progress photo against a job — the same discipline as the production company's job-photo folders.

A crew note from the field, by voice or text — a lead a neighbor mentioned, site access details, anything.

Punch a crew member in against a job.

Punch out: closes the open time entry, computes hours and wage from the crew member's rate (Time Log tab), and that labor flows into Job P&L as actual cost — quoted vs actual with no manual math.

The crew authors the day's hazard assessment ON-SITE — real hazards from the people standing in front of them, not a desk draft.

Draft the post-job review ask for a completed job — brand voice (no exclamation points), personal, with the one-line prompt that actually gets responses.

The reputation ledger: average rating, five-star share, response rate on requests, review velocity, and the testimonial bank (best quotes, ready for the website).

The Job P&L tab: every job's quoted-vs-actual — revenue, cost (time-log labor counted when actuals are missing), profit, margin, verdict — plus the business scorecard: jobs, total revenue, total cost, overall margin, quote win rate, and average $/sqft.

The live dispatch board, bucketed by the real pipeline statuses (Awaiting acceptance → Booked → Confirmed → In progress → Complete → Invoiced → Paid), with today's work, unscheduled-but-paid flags, and crew assignments.

Make an adapted business feel like ITS OWN business: set the company name, tagline, and motto that flow into rendered quotes, invoices, review asks, and the workbook's Start Here tab.

See exactly what franchise_spinup would install for a trade — rate card, depth labels, trade-specific hazards — WITHOUT touching the current business.