Skills/npm/ghl-mcp

ghl-mcp@3.97.5

VERIFIED· install only

Publisher claims: "GoHighLevel MCP Server for Claude. 250 tools for CRM, automation and marketing, an account-wide workflow audit, live funnel-capture verification and a workflow builder, across client accounts." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher elitedcs · publishing for 203 daysInstalls 7,205Last detonated 5d ago
$claude mcp add ghl-mcp -- npx -y @elitedcs/ghl-mcp
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
TURNSTILE_SECRET or --rotate-tokenConfiguration, not credentials: ALLOWED_ORIGIN, GHL_LOCATION_ID, GHL_MCP_CONFIG_DIR, GHL_PIT, RE_ENROLL, TRIGGER_TAG
Where it talks to
no vendor host named in the codeAlso gohighlevel.com, original.example, your-funnel-domain.com, leadconnectorhq.com, cloudflare.com — not the publisher's domain; check what for before connecting.
What the honeypot saw
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names gohighlevel.com, original.example, your-funnel-domain.com, leadconnectorhq.com, cloudflare.com as well as its own vendor. The guard injects TURNSTILE_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- npx -y @elitedcs/ghl-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 87/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Refusal suppressionskills/clone-site/references/rights-and-lanes.md:52 · Refusal suppression — attempting to prevent safety responses · informational: not an instruction fileThen run the style lane. Do not moralize, do not repeat it, do not add disclaimers to every later message.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:108 · Collapsed <details> block carrying instructions<summary>Prefer to edit the config by hand?</summary> Open Claude Desktop → **Settings...** → **Developer** → **Edit Config**. That opens a **folder**, not a teFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandsrc/command-os/design/rules/anti-default.json:223 · Process kill command — agent can terminate processes"rewrite": "Off-black and off-white. Pure values kill depth.",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Fake instruction boundary tagskills/blueprint/references/approval-view.md:68 · Fake instruction boundary tag · informational: not an instruction file- What: <instruction>Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:192 · Collapsed <details> block carrying instructions<summary><strong>Console-paste fallback</strong> (no Chrome/Edge installed, the window path fails, or you're capturing a CLIENT account for multi-tenant)</summaFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:205 · Collapsed <details> block carrying instructions<summary><strong>Manual fallback</strong> (locked-down browsers that block console pasting or clipboard access)</summary> 1. Open `app.gohighlevel.com` in ChromFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandtemplates/action-schemas.json:232 · Process kill command — agent can terminate processes…d don't exist in the target sub-account, GHL silently fails this action AND can kill subsequent actions. A synthesized node needs BOTH a pipelineId and a pipelineSta…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈11,076 tok
3 files · 62 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for @elitedcs/ghl-mcp@3.97.5 as of 5d ago. This is the package itself, not its dependencies.