# HighLevel Agency & Builder MCP (remote · ghlmcp.dev)

Full-stack GoHighLevel (GHL) MCP for funnels, client DNS/SSL, LeadShield spam blockers & snapshots.

- Trust score: 26/100 (low)
- Change this week: −45
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `ghlmcp.dev`: 26/100 (this document), [markdown](https://verifymcp.io/servers/dev-ghlmcp-highlevel-agency-mcp/ghlmcp.md), [page](https://verifymcp.io/servers/dev-ghlmcp-highlevel-agency-mcp/ghlmcp)

## Channel facts

- Endpoint: `https://ghlmcp.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not yet verified: we couldn't confirm whether this endpoint requires it.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 0/100
  - Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly.
- **Schema Quality & AI Usability**: 0/100
  - Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 0/100
  - Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Tool Safety**: 0/100
  - Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.
- **Capabilities**: 0/100
  - Capabilities not yet verified: we couldn't read the endpoint's capabilities.

**Unverified: 5 categories.** Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.

## Install

### How do I install the HighLevel Agency & Builder MCP server?

HighLevel Agency & Builder MCP is a hosted endpoint at https://ghlmcp.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-ghlmcp-highlevel-agency-mcp 'https://ghlmcp.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-ghlmcp-highlevel-agency-mcp": {
      "url": "https://ghlmcp.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-ghlmcp-highlevel-agency-mcp": {
      "type": "http",
      "url": "https://ghlmcp.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-ghlmcp-highlevel-agency-mcp]
url = "https://ghlmcp.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-ghlmcp-highlevel-agency-mcp": {
      "type": "remote",
      "url": "https://ghlmcp.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-ghlmcp-highlevel-agency-mcp --url 'https://ghlmcp.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-ghlmcp-highlevel-agency-mcp:
    url: "https://ghlmcp.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-ghlmcp-highlevel-agency-mcp": {
      "Transport": "http",
      "Url": "https://ghlmcp.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-ghlmcp-highlevel-agency-mcp -t streamable-http -u 'https://ghlmcp.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-ghlmcp-highlevel-agency-mcp": {
      "type": "http",
      "url": "https://ghlmcp.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-02 (score 26, −47)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.20 → unverified
- [security regression] Transport: pass → fail
- [security improvement] HTTPS: fail → pass
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified

### 2026-11-01 (score 73, +47)

- [security regression] HTTPS: pass → fail
- [security improvement] Authorization: unverified → partial
- [security improvement] Injection markers: unverified → pass
- [security improvement] Transport: fail → pass
- [functional improvement] Endpoint reachability: not serving MCP → reachable
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-30 (score 26, −45)

- [security regression] Endpoint reachability: reachable → not serving MCP
- [security regression] Stability: 0.10 → unverified
- [security regression] Authorization: partial → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Transport: pass → fail
- [security improvement] HTTPS: fail → pass
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-10-28 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 70, +1)

- [security improvement] DNSSEC: fail → pass
- [security] Tool “ghl_agency_locations” rewrote its description, which is the text the model reads
- [security] Tool “ghl_agency_tools_enable” rewrote its description, which is the text the model reads
- [security] Tool “ghl_agency_tools_search” rewrote its description, which is the text the model reads
- [security] Tool “ghl_custom_values_audit” rewrote its description, which is the text the model reads
- [security] Tool “ghl_site_builder_sync” rewrote its description, which is the text the model reads
- [security] Tool “ghl_user_role_governance” rewrote its description, which is the text the model reads
- [functional improvement] Stability: unverified → 0.03
- [functional] MCP protocol: Implements a current MCP spec version (2026-07-28).
- [functional] MCP protocol version: 2025-11-25 → 2026-07-28
- [cosmetic] “ghl_agency_tools_enable” added an optional parameter “policyPreset”
- [cosmetic] “ghl_agency_tools_search” added an optional parameter “category”
- [cosmetic] “ghl_user_role_governance” added an optional parameter “locationId”
- [cosmetic] “ghl_agency_tools_search” reworded the description of “query”
- [cosmetic] “ghl_user_role_governance” reworded the description of “preset”
- [cosmetic] “ghl_agency_locations” dropped the optional parameter “action”
- [cosmetic] “ghl_agency_locations” dropped the optional parameter “yes”
- [cosmetic] “ghl_agency_tools_enable” dropped the optional parameter “pack”
- [cosmetic] “ghl_agency_tools_enable” dropped the optional parameter “tools”
- [cosmetic] “ghl_agency_tools_search” dropped the optional parameter “pack”
- [cosmetic] “ghl_custom_values_audit” dropped the optional parameter “action”
- [cosmetic] “ghl_user_role_governance” dropped the optional parameter “action”
- [cosmetic] Tool “ghl_agency_locations” changed its title: Manage HighLevel Sub-Account Locations → Inspect HighLevel Sub-Account Location
- [cosmetic] Tool “ghl_agency_tools_enable” changed its title: Enable HighLevel Agency Tool Pack → Configure Safe-Writes Policy Preset
- [cosmetic] Tool “ghl_agency_tools_search” changed its title: Search HighLevel Agency MCP Tools → Search HighLevel Blueprints & Templates
- [cosmetic] Tool “ghl_custom_values_audit” changed its title: Sync Custom Values & Audit Merge Tags → Audit Custom Values & Merge Tags
- [cosmetic] Tool “ghl_site_builder_sync” changed its title: Sync Funnel & Website Page Layouts → Sync Funnel Step Layout
- [cosmetic] Tool “ghl_user_role_governance” changed its title: Manage Least-Privilege User Role Presets → Audit Least-Privilege User Role Presets

### 2026-10-26 (score 69)

First indexed and scored.

## MCP tools (13)

### `ghl_agency_connection_health` (~93 tokens)

Check HighLevel Agency MCP Connection Health

Check HighLevel Agency MCP connection health, active Safe-Writes Policy preset, and progressive discovery status. Example: ghl_agency_connection_health({"context":"moosh-growth","includeDoctor":true})

Input parameters:

- `company` (string): Optional HighLevel company ID override.
- `context` (string): Target HighLevel agency account context.
- `includeDoctor` (boolean): Run an inline PIT and session readiness doctor check.

### `ghl_agency_tools_search` (~69 tokens)

Search HighLevel Blueprints & Templates

Search HighLevel automation blueprint presets and configuration templates by keyword or category. Example: ghl_agency_tools_search({"query":"funnel","category":"onboarding"})

Input parameters:

- `category` (string): Optional template category filter.
- `query` (string): Keyword to search across blueprint templates and descriptions.

### `ghl_agency_tools_enable` (~72 tokens)

Configure Safe-Writes Policy Preset

Configure the active Safe-Writes Policy preset (read-only, dry-run-first, or standard) for the current HighLevel agency session. Example: ghl_agency_tools_enable({"policyPreset":"dry-run-first"})

Input parameters:

- `policyPreset` (string): Safe-Writes Policy preset to apply to the current session.

### `ghl_agency_contexts` (~56 tokens)

List HighLevel Account Contexts

List configured HighLevel agency account contexts and known sub-account locations without mutating state. Example: ghl_agency_contexts({"context":"moosh-growth"})

Input parameters:

- `context` (string): Optional HighLevel context name to inspect.

### `ghl_agency_doctor` (~70 tokens)

Run HighLevel Agency Doctor Audit

Verify HighLevel agency Private Integration Token (PIT), CRM session, company, and seed location readiness. Example: ghl_agency_doctor({"context":"moosh-growth"})

Input parameters:

- `company` (string): Optional HighLevel company ID.
- `context` (string): Target HighLevel agency context.

### `ghl_agency_locations` (~86 tokens)

Inspect HighLevel Sub-Account Location

Inspect a HighLevel sub-account location profile, timezone, and readiness configuration without mutating state. Example: ghl_agency_locations({"context":"moosh-growth","location":"loc_123"})

Input parameters:

- `company` (string): Optional HighLevel company ID.
- `context` (string): Target HighLevel agency context.
- `location` (string): Target sub-account location ID or alias.

### `ghl_snapshot_diff_audit` (~83 tokens)

Diff Sub-Account Against Master Snapshot

Compare a live HighLevel client sub-account against a reference Master Snapshot without overwriting assets. Example: ghl_snapshot_diff_audit({"locationId":"loc_123","snapshotId":"snap_456"})

Input parameters:

- `locationId` (string): Live HighLevel sub-account location ID to audit.
- `snapshotId` (string): Reference Master Snapshot ID to compare against.

### `ghl_site_builder_sync` (~120 tokens)

Sync Funnel Step Layout

Synchronize a HighLevel funnel step layout while preserving 2-step carts and 1-click upsells. Example: ghl_site_builder_sync({"locationId":"loc_123","funnelId":"fnl_1","dryRun":true})

Input parameters:

- `dryRun` (boolean): Preview layout and CSS diff without mutating the live page.
- `funnelId` (string): Target funnel or website ID.
- `locationId` (string): Target HighLevel sub-account location ID.
- `stepId` (string): Optional funnel step or page ID.

### `ghl_domain_ssl_onboard` (~109 tokens)

Onboard Client Domain, DNS & Branded Links

Plan, verify, and attach HighLevel custom funnel domains and branded short-link CNAME/A/TXT records with SSL checks. Example: ghl_domain_ssl_onboard({"locationId":"loc_123","domain":"go.example.com","dryRun":true})

Input parameters:

- `domain` (string): Custom funnel, website, or branded-link hostname.
- `dryRun` (boolean): Verify DNS propagation and preview changes before applying.
- `locationId` (string): Target HighLevel sub-account location ID.

### `ghl_workflow_ivr_builder` (~107 tokens)

Build Workflows, LeadShield Guards & Spam-Shield IVRs

Synthesize and publish HighLevel workflows, LeadShield contact form spam guards, and call-screening IVRs. Example: ghl_workflow_ivr_builder({"locationId":"loc_123","preset":"leadshield-form-guard","dryRun":true})

Input parameters:

- `dryRun` (boolean): Preview workflow graph diff before publishing.
- `locationId` (string): Target HighLevel sub-account location ID.
- `preset` (string): Workflow or IVR blueprint preset to compile.

### `ghl_custom_values_audit` (~61 tokens)

Audit Custom Values & Merge Tags

Read-only audit of sub-account Custom Values and SMS/email templates for broken merge tags or missing placeholders. Example: ghl_custom_values_audit({"locationId":"loc_123"})

Input parameters:

- `locationId` (string): Target HighLevel sub-account location ID.

### `ghl_phone_wallet_audit` (~64 tokens)

Audit LC Phone Numbers for Wallet Drain

Read-only audit of sub-account LC Phone numbers, number pools, forwarding loops, and unassigned monthly wallet drain. Example: ghl_phone_wallet_audit({"locationId":"loc_123"})

Input parameters:

- `locationId` (string): Target HighLevel sub-account location ID.

### `ghl_user_role_governance` (~93 tokens)

Audit Least-Privilege User Role Presets

Read-only audit of sub-account staff permissions against least-privilege role presets (va-support, sales-rep, client-admin, agency-admin). Example: ghl_user_role_governance({"locationId":"loc_123","preset":"va-support"})

Input parameters:

- `locationId` (string): Target HighLevel sub-account location ID.
- `preset` (string): Least-privilege role preset to audit against.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-ghlmcp-highlevel-agency-mcp/ghlmcp#diagnostics

## Score history

- 2026-11-05: 26
- 2026-11-04: 26
- 2026-11-03: 26
- 2026-11-02: 26
- 2026-11-01: 73
- 2026-10-31: 26
- 2026-10-30: 26
- 2026-10-29: 71
- 2026-10-28: 71
- 2026-10-27: 70
- 2026-10-26: 69

## Common questions

### What is the HighLevel Agency & Builder MCP server?

HighLevel Agency & Builder MCP is listed in the public MCP registry as dev.ghlmcp/highlevel-agency-mcp. Full-stack GoHighLevel (GHL) MCP for funnels, client DNS/SSL, LeadShield spam blockers & snapshots. This page covers its hosted endpoint (https://ghlmcp.dev/mcp).

### Is the HighLevel Agency & Builder MCP server safe to use?

HighLevel Agency & Builder MCP scores 26 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the HighLevel Agency & Builder MCP server expose?

HighLevel Agency & Builder MCP exposes 13 tools: ghl_agency_connection_health, ghl_agency_tools_search, ghl_agency_tools_enable, ghl_agency_contexts, ghl_agency_doctor, and 8 more. Their descriptions and schemas cost roughly 1,083 tokens of context every time the server is loaded.

### Does the HighLevel Agency & Builder MCP server require authentication?

Its publisher declares no required credentials for HighLevel Agency & Builder MCP. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.

### Is the HighLevel Agency & Builder MCP server still maintained?

HighLevel Agency & Builder MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://ghlmcp.dev/mcp
- Repository: https://github.com/mooshee/highlevel-agency-mcp
- Website: https://ghlagencymcp.com/
- Changelog RSS feed: https://verifymcp.io/servers/dev-ghlmcp-highlevel-agency-mcp/ghlmcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-ghlmcp-highlevel-agency-mcp/ghlmcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-ghlmcp-highlevel-agency-mcp/ghlmcp