Researches the account, writes the sequence, keeps the CRM current, and books the meeting without four tabs.
Built for: The account executive whose pipeline is accurate only on the days they spend an hour updating it by hand.
The button opens the checkout, where 8 servers and 4 skills are listed one by one with what each does to the bill — free, already yours, monthly or a one-off licence. Nothing is charged until you confirm it there, in Stripe’s own card frame on that page rather than a redirect, and each paid member keeps its own budget cap.
The reason to buy a stack rather than five listings: each line below needs more than one member connected at the same time.
Read and update accounts, contacts and opportunities in Salesforce, and note what was said instead of remembering it.
Research a company before the call through search and Perplexity, and keep the finding on the record.
Draft the outreach sequence with the follow-up cadence and the compliance footer already in it.
Find the free slot and put the meeting in the calendar the invitation will come from.
What each part contributes, and why it was picked over the obvious alternative. Prices and permissions are read from the listings, so nothing here can disagree with the catalogue.
The system of record, with the breadth to cover data operations rather than only reading a contact.
The marketing side of the same account — forms, lifecycle, the app your team already builds against.
Scope-gated mail access with path jails on attachments, which is the version of an inbox connector worth giving a sales tool.
Finding the slot and putting the meeting in it, from the same conversation that agreed to it.
Where the account notes, the call summary and the internal answer to 'what happened last time' live.
Google web, news and places search for the pre-call research that decides how the first two minutes go.
The structured list the team actually works from — territories, target accounts, sequences — when the CRM view is too heavy.
The quick answer with sources about a company or a market, for the question that arrives ten minutes before the call.
Writes the outreach sequence with cadence, personalisation and deliverability treated as part of the copy rather than as an afterthought.
Geocoding, place search and routing for field sales: which accounts are near each other, and what a day of visits actually looks like.
The invoice or payment request at the end of a small deal, generated as a PDF from the record rather than typed into a template.
Drives a browser for the research a search API cannot reach — a portal, a pricing page behind a form, a directory with no API.
Every member is a subscription or a licence bought once, so the monthly figure is a price rather than an estimate: what moves it is adding or dropping a member, not how hard the stack is worked. The one assumption is that a one-off licence is spread over a year so it can sit in the same column as a subscription.
| Part | What you are paying for | Monthly, as quoted |
|---|---|---|
| Salesforce | Free | — |
| Hubspot | Free | — |
| Gmail | from $15/mo | $15/mo |
| Google Calendar | Free | — |
| Notion | Free | — |
| Serper Search | Free | — |
| Airtable | Free | — |
| Perplexity Ask | Free | — |
| Skills | ||
| cold-email | $35 · $2.92/mo over 12 months | $2.92/mo |
| Google Maps (gmaps) | $29 · $2.42/mo over 12 months | $2.42/mo |
| Invoice Generator | Free · context cost only | — |
| agent-browser core | Free · context cost only | — |
| Everything above | $15 of servers plus $5.00 of skills, the same in a quiet month and a busy one | $20/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. One-off purchases in this stack total $64 — cold-email $35, Google Maps (gmaps) $29 — paid once and spread here so they sit in the same column as a subscription. Everything arrives on one mcprush invoice, taken by Stripe from the card on your account, not one per publisher — mcprush.com is the merchant of record and each publisher is paid out of it.
Install only these and the bill is nothing: 7 servers and 2 skills.
Left out, and what goes with it:
Gmail at from $15/mo. Each of those plans states the calls it includes in a month, and running past one never arrives as a larger invoice: the gateway refuses the call over the allowance and returns an MCP error naming the plan. The figure above is what the stack costs in a busy month as well as a quiet one — what a heavy month changes is which plan you need, not what this one bills.
Budget caps are set per install and enforced at the gateway, so a retry loop is refused at the cap rather than left to run through an allowance overnight.
One step per part, in the order they are useful: connect what the work reads before what it writes, and install the skills that decide how the work is done last. Each step is a command you can read before you run it.
npx mcprush@latest stack add sales-deskNothing in this stack installs from one command today: 12 members are either paid, run from its own source, or a skill with its own command — the steps above name each one. Nothing is connected until you approve it.
Installed together, these tool surfaces add up. It is the first thing a security reviewer asks for, so what has been counted — and what nobody has counted yet — is on the page rather than in a PDF.
| Member | Tool surface | Write tools |
|---|---|---|
| Airtable | not imported | not recorded |
| Gmail | not imported | not recorded |
| Google Calendar | not imported | not recorded |
| Hubspot | not imported | not recorded |
| Notion | not imported | not recorded |
| Perplexity Ask | not imported | not recorded |
| Salesforce | not imported | not recorded |
| Serper Search | not imported | not recorded |
A stack's blast radius is the union of its members, not the worst of them. That union cannot be taken here, because 8 members of 8 have no imported tool surface — so the figure a review asks for is missing rather than low, and a member marked not imported is one nobody has counted rather than one that cannot write.
A stack is a default, not a verdict. These are the substitutions the maintainer would make, and what each one costs or saves.
A small team that never bought Salesforce runs the same desk against Close, and loses the parts of the sequence that assumed enterprise objects.
If marketing automation is the only part of HubSpot you use, the narrower server does that job and takes the CRM overlap out of the stack.
Written by the maintainer, kept on the page rather than in a support thread.
It cannot send mail on your behalf without you. The drafting is the desk's; hitting send stays a person's action and should stay a person's permission.
It does not price anything. Discounts, terms and approvals live in your own process, not in a prompt.
The CRM is the record. Where the desk and Salesforce disagree, Salesforce is right and the desk is stale — nothing here is a second system of record.
A stack has an owner: whoever keeps it re-checks the combination when a member changes, and the members themselves are published by the people named on each row.
One place for the notes, the tasks, the calendar and the inbox, with a memory that survives the session.
Reads the ticket, finds whether it is a bug or a billing question, and drafts the reply in your own voice.
Finds the sources, keeps what it read, and answers with a citation that still opens next quarter.