Write something
Pinned
25d •
Read/write vs. build: GHL Command and the official HighLevel MCP
HighLevel now ships an official MCP for Claude. It is free, it is genuinely good, and several of you asked where that leaves GHL Command. This post is the permanent answer. The one-line version: the official MCP reads and writes your CRM. GHL Command builds and fixes it. They stack fine together. The side-by-side, verified against HighLevel's own docs: • Build, edit, and publish workflows: official MCP, no. GHL Command, yes, the full builder. • Deep workflow cloning with every internal ID remapped: official, no. GHL Command, yes. • The silent-failure audit, catching actions that point at deleted stages and fields, which GHL skips with no error: official, no. GHL Command, yes. • Funnels and landing pages: official, no. GHL Command, yes, and recently proven live. • Forms: official reads them only. GHL Command builds them, fields, logic, auto-responder. • Pipelines: official lists them. GHL Command creates and edits them. • Whole-account provisioning: official, no. GHL Command, yes. Blueprint builds a client sub-account from one intake. • Setup: the official MCP wins here, one-click OAuth. Ours is a token plus a one-time Firebase step, and that extra setup is exactly what powers the builders. • Cost: the official MCP is included with your GHL plan. GHL Command is $97 a month for unlimited sub-accounts, with a free read-only tier that includes the audit. Why the difference exists: the public API has no write access to workflows, funnels, or forms, and never has. The official MCP is built on the public API, so it inherits that ceiling. GHL Command works the same internal routes GHL's own builders use, which is harder to maintain and worth it, because building is the part that eats your week. If you only need Claude to read and write your CRM, use the official MCP. It is excellent and free. If you want Claude to actually build and fix your automations, funnels, forms, and whole client accounts, that is GHL Command, and today it is the only thing that does it. And if you want to see what "we maintain the hard part" looks like in practice, the Green Doesn't Mean Working course in the classroom walks a real bug from customer email to shipped fix in one day.
Pinned
Jun 2 •
Start here — Welcome to GHL Command
Welcome in. You're a founding member, and I don't take that lightly. Quick on what this is. GHL Command is the room for agency owners who use AI to actually run their operations, not just market with it. I run a healthcare agency on this exact stack every day: the GHL Command MCP, Claude, and a small team of named agents. This is where I build it in public, drop the prompts and templates I'm using, and answer your GoHighLevel questions directly. What your membership includes, plainly: - The GHL Command tool (your license) at the founding rate of $97/mo, locked as long as you stay subscribed. - This community: the build-in-public room, the prompts and templates, and me answering questions. - Every new tool we ship, automatically, at no extra cost while you're a member. Billing lives in your account, not here. You can manage or cancel anytime. If you cancel, the license and your spot here wind down together. Simple. Your first 20 minutes: 1. Open the Start Here course in the Classroom. It gets GHL Command installed and gives you a real win in about 10 minutes (point Claude at one of your sub-accounts and have it tell you what's silently broken). 2. Come back and introduce yourself below: who you are, how many sub-accounts you run, and the one GHL task you're most tired of doing by hand. 3. Read the first war story I pinned: "The $5,000 pipeline ID mistake every GHL agency owner makes." It's the bug that started all of this. That's it. Get the tool running, get your first win, then tell me what you want me to build next. This thing grows around what you actually need. — Jerry
Pinned
Jun 2 •
Why GHL Command exists
I'm a doctor. I spent years building Practice Naturals (functional medicine brand) and Clinic Launch Lab (consulting for new practices). Built apps. Built an agency (Elite DC's) running GHL sub-accounts for healthcare brands. About a year ago I added AI to everything. Hourly outputs got better. Daily decisions got faster. The operational headaches stayed the same. Here's the thing nobody says out loud about GHL agency work: the platform is incredibly powerful, but it punishes you for being human. • Forget to update a pipeline ID in one workflow? The next 12 actions silently fail and your client wonders why nothing's happening. • Submit an A2P registration with one wrong field? Denied, no diagnostic, start over. • Running 5 sub-accounts? Sure. 15? Now you can't keep straight in your head. • Want to know which clients have broken automations RIGHT NOW? Pull each sub-account, click through each workflow, hope you remember what you checked. I started building tools to solve these for myself. The result is GHL Command. A system of AI agents that watches my entire agency operation and tells me what needs attention. Atlas is the orchestrator. Vera watches deploys for safety. Sasha handles A2P. Hugo monitors sub-account health. Marcus runs campaigns. Iris handles client onboarding. I'm building it in public, in this community, starting this week. Vera ships this week. The tool license is bundled with your membership. Cancel and you lose access. That's the deal. This community is for GHL agency owners who think the platform should work harder than they do. Not for general "AI for marketers" content. Not for theoretical agency advice. Real stack, real wins, real failures. If that's you, you're in the right place. Dr. Jerry
1
0
11m •
Age Every Deal in the Pipeline
Command note: a pipeline full of open deals looks like momentum. Most of the time it is a graveyard. Nobody moves a card to Lost voluntarily. So stages fill with deals that stopped moving weeks ago, and the forecast quietly becomes fiction. The command I run: "List every open opportunity in this pipeline. Show days since last activity and current stage. Group them into moving, stalled over 14 days, and dead over 30." What comes back: • The stage deals actually die in, which is rarely the one you would guess • A short list worth a real follow-up today • A longer list that should be closed out or moved to nurture Do this with it: 1) Run it on every client pipeline once a week. Same day, same time. 2) Close out anything past 30 days. A clean pipeline beats a big one. 3) For the stalled bucket, ask what the stage was missing. Usually a task or an automation that never fired. 4) Fix the stage, not the deal. One fix clears the next fifty. Aging a pipeline is not a report you read. It is maintenance you perform. A pipeline you never prune stops being a forecast and starts being a story you tell yourself.
0
0
1d •
Test Every Automation on One Contact
Command note: the account you break is always the one you were sure about. Every automation looks fine in the builder. The builder is not where it fails. It fails against real data: a contact with no last name, a tag that never got removed, a stage nobody uses anymore. So before anything runs on a list, run it on one. Make a single test contact in every sub-account you manage: • Your own email and phone, never the client's • Tagged so you can find it in two seconds • Left in the account permanently, not deleted after launch Then use it every time: 1) Publish the workflow and add the test contact first, nobody else. 2) Watch the full path end to end, not just the first action. 3) Check what actually landed: the SMS text, the merge fields, the timing. 4) Confirm it ends. The contact exits, or the goal fires. 5) Only then open it to the real list. This costs you four minutes. A bad send costs you the account. The same rule applies when AI builds it. AI can assemble a workflow faster than you can read it, which means the test contact matters more, not less. Speed of build raises the value of the check. One contact tells you the truth before four hundred tell your client.
0
0
1-30 of 67
Suggested communities
Powered by