@elitedcs/ghl-mcp 3.54.0 → 3.56.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +45 -0
- package/README.md +40 -6
- package/dist/index.js +485 -179
- package/package.json +4 -3
- package/skills/blueprint/README.md +27 -0
- package/skills/blueprint/SKILL.md +149 -0
- package/skills/blueprint/examples/medspa-approval-view.md +92 -0
- package/skills/blueprint/examples/medspa-brief.json +52 -0
- package/skills/blueprint/examples/medspa-build-plan.json +265 -0
- package/skills/blueprint/examples/medspa-dry-run-report.md +67 -0
- package/skills/blueprint/examples/sample-approval-view.md +82 -0
- package/skills/blueprint/examples/sample-brief.json +13 -0
- package/skills/blueprint/examples/sample-build-plan.json +227 -0
- package/skills/blueprint/examples/validate-plan.cjs +127 -0
- package/skills/blueprint/presets/clinic-launch-a2p.md +39 -0
- package/skills/blueprint/presets/clinic-launch-a2p.preset.json +337 -0
- package/skills/blueprint/presets/generic-client.md +36 -0
- package/skills/blueprint/presets/generic-client.preset.json +255 -0
- package/skills/blueprint/presets/med-spa.md +59 -0
- package/skills/blueprint/presets/med-spa.preset.json +264 -0
- package/skills/blueprint/references/agency-os-detection.md +80 -0
- package/skills/blueprint/references/approval-view.md +83 -0
- package/skills/blueprint/references/brief-schema.md +45 -0
- package/skills/blueprint/references/build-plan-schema.md +52 -0
- package/skills/blueprint/references/external-funnel.md +310 -0
- package/skills/blueprint/references/intake-question-set.md +141 -0
- package/skills/blueprint/references/preset-format.md +130 -0
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,50 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 3.56.0 — Security off-switches: any tool can be disabled; sub-account create/delete is opt-in
|
|
4
|
+
|
|
5
|
+
Shaped directly by subscriber feedback: some teams keep account-level
|
|
6
|
+
operations human-only, so a prompt-injected or misbehaving AI session can
|
|
7
|
+
never touch them. Two new controls, both enforced at server startup from
|
|
8
|
+
your config — there is deliberately NO way to change them from inside a
|
|
9
|
+
Claude conversation.
|
|
10
|
+
|
|
11
|
+
- **Sub-account create/delete is now OFF by default.** `create_sub_account`
|
|
12
|
+
and `delete_sub_account` register only when `GHL_ENABLE_ACCOUNT_ADMIN=1`
|
|
13
|
+
is set. The setup wizard asks (default No). The allowlist cannot bypass
|
|
14
|
+
the flag. If you were using these tools, add the flag and restart.
|
|
15
|
+
- **Universal deny-list**: `GHL_DISABLED_TOOLS` / `GHL_DISABLED_MODULES`
|
|
16
|
+
switch off any tool or module. A disabled tool never registers — it is
|
|
17
|
+
invisible to the model, so it can't be called *or discovered* from a
|
|
18
|
+
conversation. Deny wins over the allowlist and the always-on set,
|
|
19
|
+
including the credential helpers (`enable_workflow_builder`,
|
|
20
|
+
`auto_capture_firebase_script`, `capture_firebase_interactive`) and
|
|
21
|
+
`install_skills` (denying it also skips the bundled-skills auto-install).
|
|
22
|
+
- **Un-brickable**: the recovery core (`setup_ghl_mcp`, `request_license`,
|
|
23
|
+
`get_mcp_version`, `health_check`) ignores denial, with a logged warning.
|
|
24
|
+
- **Verifiable**: `health_check` gained a "Tool gating" section reporting
|
|
25
|
+
exactly what's disabled, whether account admin is on, and any misspelled
|
|
26
|
+
name in your gating vars (typos do NOT disable anything — they warn).
|
|
27
|
+
- Advertised default tool count is now 233 (235 with account admin enabled).
|
|
28
|
+
- README: new "Turning tools off (security)" section with examples.
|
|
29
|
+
|
|
30
|
+
## 3.55.0 — Skills ship inside the package: Blueprint installs itself
|
|
31
|
+
|
|
32
|
+
The gap between "the tools exist" and "the guided experience exists" is
|
|
33
|
+
closed. The npm package now bundles guided skills and installs them into
|
|
34
|
+
your `~/.claude/skills/` automatically on every start — nothing to download,
|
|
35
|
+
no separate zip.
|
|
36
|
+
|
|
37
|
+
- **Blueprint is now actually delivered**: the full guided skill (intake →
|
|
38
|
+
brief → build plan → approval → staged build) that orchestrates the six
|
|
39
|
+
Blueprint tools ships in the package. Previously the README sold it but
|
|
40
|
+
only the raw tools shipped.
|
|
41
|
+
- Installer is idempotent and never clobbers your edits: files you've
|
|
42
|
+
modified are kept and reported, updates only touch files the installer
|
|
43
|
+
itself wrote (tracked by content hash in `.ghl-command-skills.json`).
|
|
44
|
+
- New `install_skills` tool (every tier — it only writes to your machine)
|
|
45
|
+
to verify what's installed or repair a deleted skill.
|
|
46
|
+
- Restart Claude fully after an update so new skills load.
|
|
47
|
+
|
|
3
48
|
## 3.54.0 — Page Studio: `compose_page` + `compose_website` build designer-grade pages
|
|
4
49
|
|
|
5
50
|
The gap between "GHL Command creates funnels/websites" and "the pages look
|
package/README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
# GHL Command — GoHighLevel MCP Server
|
|
2
2
|
|
|
3
|
-
**Full GoHighLevel API access for Claude.**
|
|
3
|
+
**Full GoHighLevel API access for Claude.** 233 tools across 49 modules — manage contacts, conversations, pipelines, calendars, funnels, workflows, invoices, custom objects, webhooks, and more. **Includes full workflow builder, funnel/page editor, form builder, pipeline builder, bulk operations, account export, and workflow cloning** — capabilities no other GHL tool offers. **Multi-tenant:** one install can run the workflow builder across multiple clients' GHL accounts.
|
|
4
4
|
|
|
5
5
|
**Distributed via npm as [`@elitedcs/ghl-mcp`](https://www.npmjs.com/package/@elitedcs/ghl-mcp).** Buyers install with one config block — no git, no Node.js setup, no terminal commands. Updates flow automatically (`npx @latest` re-resolves on every Claude restart).
|
|
6
6
|
|
|
@@ -8,9 +8,11 @@ Works with **both the Claude Desktop App and Claude Code terminal** — your cho
|
|
|
8
8
|
|
|
9
9
|
**License required.** Get it at [ghlcommand.com](https://ghlcommand.com?utm_source=npm&utm_medium=readme) — $97/mo, covering UNLIMITED GoHighLevel sub-accounts on up to 3 machines (never billed per account). **30-day time-back guarantee**: save 5+ hours on one client build or your first month back.
|
|
10
10
|
|
|
11
|
-
**Try it FREE (read-only tier).** Grab an instant free key at [ghlcommand.com/free](https://ghlcommand.com/free?utm_source=npm&utm_medium=readme) —
|
|
11
|
+
**Try it FREE (read-only tier).** Grab an instant free key at [ghlcommand.com/free](https://ghlcommand.com/free?utm_source=npm&utm_medium=readme) — 107 read-only tools on your own GHL account (89 before the one-login auditor unlock): the account-wide workflow audit (`audit_workflows` finds the silently broken references GHL never warns you about), account health, and every read across contacts, pipelines, funnels, and workflows. Write tools stay visible and answer with upgrade info. Buying later with the same email upgrades your key in place — 1 machine on free, 3 when you upgrade.
|
|
12
12
|
|
|
13
|
-
**How this differs from HighLevel's official MCP.** HighLevel ships an official Anthropic MCP that reads and writes your CRM (contacts, conversations, calendars, opportunities, payments, social) over the public API — it's free and it's good; use it for that. What it *cannot* do, because the public API doesn't expose it: **build or edit workflows, build funnels/landing pages, or build forms.** That's exactly what GHL Command does — the programmatic Workflow Builder, funnel/page builder, form builder, deep workflow cloning, the silent-failure `audit_workflows`, and Blueprint (build a whole client account from one
|
|
13
|
+
**How this differs from HighLevel's official MCP.** HighLevel ships an official Anthropic MCP that reads and writes your CRM (contacts, conversations, calendars, opportunities, payments, social) over the public API — it's free and it's good; use it for that. What it *cannot* do, because the public API doesn't expose it: **build or edit workflows, build funnels/landing pages, or build forms.** That's exactly what GHL Command does — the programmatic Workflow Builder, funnel/page builder, form builder, deep workflow cloning, the silent-failure `audit_workflows`, and Blueprint (build a whole client account from one intake — ships as a guided skill that **installs itself automatically** with this package; nothing to download), all on GHL's internal APIs. **Official MCP = read/write your CRM. GHL Command = build and fix it.** They stack fine together.
|
|
14
|
+
|
|
15
|
+
**Bundled skills (install automatically).** The package ships guided skills that teach Claude complete multi-step workflows on top of the raw tools. On every start the server installs/updates them into your `~/.claude/skills/` (never overwriting files you've edited — your version wins and is reported). Current skills: **Blueprint** — turn one client intake into a complete reviewed GHL account build. Verify or repair any time by asking Claude to `run install_skills`, then fully restart Claude so new skills load.
|
|
14
16
|
|
|
15
17
|
Built by [Elite DCs, LLC](https://elitedcs.com).
|
|
16
18
|
|
|
@@ -120,7 +122,7 @@ Run setup_ghl_mcp to activate GHL Command:
|
|
|
120
122
|
ghl_location_id: YOUR_LOCATION_ID
|
|
121
123
|
```
|
|
122
124
|
|
|
123
|
-
Approve the tool call. Server validates your license, verifies your GHL credentials, writes them to a per-user config file. **Quit Claude one more time and reopen** — the full core toolset is now unlocked (
|
|
125
|
+
Approve the tool call. Server validates your license, verifies your GHL credentials, writes them to a per-user config file. **Quit Claude one more time and reopen** — the full core toolset is now unlocked (233 tools total with the optional Workflow Builder Firebase add-on).
|
|
124
126
|
|
|
125
127
|
### 4. Try it
|
|
126
128
|
|
|
@@ -160,7 +162,7 @@ https://app.gohighlevel.com/v2/location/YOUR_LOCATION_ID/dashboard
|
|
|
160
162
|
|
|
161
163
|
## Enable the Workflow Builder
|
|
162
164
|
|
|
163
|
-
The builder + cloner + validator tools (workflow builder, funnel builder, form builder, pipeline builder, workflow cloner, validate_workflow) use GHL's internal API and require Firebase credentials. Without them, the other
|
|
165
|
+
The builder + cloner + validator tools (workflow builder, funnel builder, form builder, pipeline builder, workflow cloner, validate_workflow) use GHL's internal API and require Firebase credentials. Without them, the other 179 tools work fine — you just won't have workflow/funnel/form/pipeline editing. This is the flagship feature: do this step.
|
|
164
166
|
|
|
165
167
|
**One-click capture (v3.49.0+, the supported path):**
|
|
166
168
|
|
|
@@ -749,7 +751,7 @@ Source repo is private. Contributors need an invitation from `drjerryrelth`. The
|
|
|
749
751
|
|
|
750
752
|
### Reducing context / token usage
|
|
751
753
|
|
|
752
|
-
Every registered MCP tool's schema is shipped to the model on every message. With
|
|
754
|
+
Every registered MCP tool's schema is shipped to the model on every message. With 233 tools that's a meaningful per-message context cost even in chats that never touch GHL. If you only use a slice of GHL Command, restrict the tool surface with `GHL_ENABLED_MODULES` and/or `GHL_ENABLED_TOOLS`:
|
|
753
755
|
|
|
754
756
|
```jsonc
|
|
755
757
|
// Claude Desktop config — enable whole modules
|
|
@@ -784,6 +786,38 @@ Rules of the road:
|
|
|
784
786
|
|
|
785
787
|
`contacts`, `conversations`, `opportunities`, `calendars`, `locations`, `workflows`, `funnels`, `forms`, `surveys`, `payments`, `products`, `invoices`, `campaigns`, `users`, `media`, `social-planner`, `courses`, `businesses`, `blogs`, `emails`, `trigger-links`, `custom-objects`, `associations`, `estimates`, `coupons`, `webhooks`, `documents`, `bulk-operations`, `account-export`, `template-deployer`, `workflow-builder`, `funnel-builder`, `form-builder`, `pipeline-builder`, `workflow-cloner`, `smart-lists`, `reputation`, `email-campaigns`, `email-builder`, `memberships`, `validators`, `diagnostics`, `location-switcher`
|
|
786
788
|
|
|
789
|
+
### Turning tools off (security)
|
|
790
|
+
|
|
791
|
+
Some teams keep certain operations human-only — for example sub-account management or messaging — so that a prompt-injected or misbehaving AI session can never touch them. Two controls exist for exactly that:
|
|
792
|
+
|
|
793
|
+
**1. Sub-account create/delete is OFF by default.** `create_sub_account` and `delete_sub_account` do not register unless you explicitly opt in:
|
|
794
|
+
|
|
795
|
+
```jsonc
|
|
796
|
+
"env": {
|
|
797
|
+
"GHL_ENABLE_ACCOUNT_ADMIN": "1" // exactly "1" — nothing else enables it
|
|
798
|
+
}
|
|
799
|
+
```
|
|
800
|
+
|
|
801
|
+
The setup wizard asks this question during install (default No). Listing these tools in `GHL_ENABLED_TOOLS` does **not** bypass the flag.
|
|
802
|
+
|
|
803
|
+
**2. Any tool or module can be switched off** with a deny-list:
|
|
804
|
+
|
|
805
|
+
```jsonc
|
|
806
|
+
"env": {
|
|
807
|
+
"GHL_DISABLED_TOOLS": "send_message,bulk_delete_contacts",
|
|
808
|
+
"GHL_DISABLED_MODULES": "snapshots"
|
|
809
|
+
}
|
|
810
|
+
```
|
|
811
|
+
|
|
812
|
+
How the deny-list behaves:
|
|
813
|
+
|
|
814
|
+
- **Deny wins over everything** — the allowlist, the always-on set, and `GHL_ENABLE_ACCOUNT_ADMIN`. A denied tool **never registers**: it is invisible to the model, so it cannot be called *or discovered* from a conversation.
|
|
815
|
+
- **There is deliberately no tool to change gating from inside Claude.** Turning something back on requires editing your config file and fully restarting Claude — a human action.
|
|
816
|
+
- **Recovery core stays reachable:** `setup_ghl_mcp`, `request_license`, `get_mcp_version`, and `health_check` ignore denial (with a logged warning) so you can never brick your install. Everything else — including the Firebase credential helpers `enable_workflow_builder`, `auto_capture_firebase_script`, `capture_firebase_interactive`, and `install_skills` (denying it also skips the bundled-skills auto-install) — is deniable.
|
|
817
|
+
- **Verify it took effect:** run `health_check` in Claude. Its "Tool gating" section shows exactly what's disabled, whether account admin is on, and flags any misspelled name in your gating vars (typos do NOT disable anything — they warn instead).
|
|
818
|
+
- Single-location shops that never want cross-account movement can also deny `switch_location` and `register_location`.
|
|
819
|
+
- Honest limit: this gate is enforced at server startup from your config file, so it is as strong as your machine's file permissions. What it guarantees is that nothing *inside a Claude conversation* can widen the tool surface.
|
|
820
|
+
|
|
787
821
|
---
|
|
788
822
|
|
|
789
823
|
## Troubleshooting
|