# HighLevel Agency & Builder MCP

> Review HighLevel changes. Built by Moosh Works (https://mooshworks.com).

- name: io.github.mooshee/highlevel-agency-mcp
- version: 1.1.4
- connection class: R0 (autonomous)
- trust: 92/100 flags: duplicate-repo
- quality: 75/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.mooshee%2Fhighlevel-agency-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.mooshee%2Fhighlevel-agency-mcp/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 98
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-96% +updated-8d-ago -duplicate-repo(4 names)
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 75/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 13 of 13 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,939 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 48 tool changes in 30 days
- fail `stability.rug_pull`: 42 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 13, about 1,939 tokens to load them all
- tool set hash: 9b3ed9482ff1388b486fa5ce5b6f6908
- tools last changed: 2026-11-01T11:42:26.836Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.mooshee/highlevel-agency-mcp.svg)](https://protogrid.dev/servers/io.github.mooshee/highlevel-agency-mcp)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-11-01 `ghl_user_role_governance` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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"})
  - after: Compare staff assigned to the connected sub-account with a selected permission preset. This audit does not change roles.
- 2026-11-01 `ghl_phone_wallet_audit` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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"})
  - after: Inspect connected-account phone numbers, number pools, missing routing, and forwarding loops. Routing risks do not establish charges or savings.
- 2026-11-01 `ghl_custom_values_audit` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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"})
  - after: Find blank custom values, unresolved placeholders, and broken references in the connected sub-account's message templates. Optional supplied templates are checked too.
- 2026-11-01 `ghl_workflow_ivr_builder` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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})
  - after: Preview a form-screening, intake, or call-menu workflow, then apply that preview. For multi-step-intake, provide formId and input.tags (one to ten existing tag IDs), input.taskTitle and input.taskBody. Draft creation and publication are separate requested actions.
- 2026-11-01 `ghl_domain_ssl_onboard` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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})
  - after: Preview and save a domain record and funnel binding. Report DNS and HTTPS readiness separately. Hosting attachment, page routing and publication require separate steps.
- 2026-11-01 `ghl_site_builder_sync` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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})
  - after: Read a funnel page or preview layout, style, copy, or content changes. Apply the returned preview to the same page. Existing checkout and upsell components must be preserved.
- 2026-11-01 `ghl_snapshot_diff_audit` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: 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"})
  - after: Compare a supplied snapshot export with this sub-account's live custom values, custom fields, tags and calendars. Include the snapshot ID and at least one asset category. The export is user-supplied; its ownership and freshness are unverified. Missing categories remain unverified. This does not overwrite assets.
- 2026-11-01 `ghl_agency_locations` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: Inspect a HighLevel sub-account location profile, timezone, and readiness configuration without mutating state. Example: ghl_agency_locations({"context":"moosh-growth","location":"loc_123"})
  - after: Read the location profile, timezone and configuration for the connected sub-account.
- 2026-11-01 `ghl_agency_doctor` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: Verify HighLevel agency Private Integration Token (PIT), CRM session, company, and seed location readiness. Example: ghl_agency_doctor({"context":"moosh-growth"})
  - after: Check the connected account and access to custom values, calendars, and workflows. Report unavailable permissions separately.
- 2026-11-01 `ghl_agency_contexts` changed (title, description, inputSchema, annotations) **meaning changed**
  - before: List configured HighLevel agency account contexts and known sub-account locations without mutating state. Example: ghl_agency_contexts({"context":"moosh-growth"})
  - after: Show the sub-account selected during connection. Connect again to choose a different sub-account.

Full history: https://api.protogrid.dev/v1/servers/io.github.mooshee%2Fhighlevel-agency-mcp/changes

## Remotes

- https://ghlagencymcp.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.9583333)

## Packages

_none_

## Tools (13)

- `ghl_agency_connection_health`: Check access to the connected sub-account and whether builder access is available.
- `ghl_agency_contexts`: Show the sub-account selected during connection. Connect again to choose a different sub-account.
- `ghl_agency_doctor`: Check the connected account and access to custom values, calendars, and workflows. Report unavailable permissions separately.
- `ghl_agency_locations`: Read the location profile, timezone and configuration for the connected sub-account.
- `ghl_agency_tools_enable`: Choose read-only access or allow changes after a preview. Every change still requires dryRun=false and the returned preview ID.
- `ghl_agency_tools_search`: Find tools and workflow templates by keyword or category.
- `ghl_custom_values_audit`: Find blank custom values, unresolved placeholders, and broken references in the connected sub-account's message templates. Optional supplied templates are checked too.
- `ghl_domain_ssl_onboard`: Preview and save a domain record and funnel binding. Report DNS and HTTPS readiness separately. Hosting attachment, page routing and publication require separate steps.
- `ghl_phone_wallet_audit`: Inspect connected-account phone numbers, number pools, missing routing, and forwarding loops. Routing risks do not establish charges or savings.
- `ghl_site_builder_sync`: Read a funnel page or preview layout, style, copy, or content changes. Apply the returned preview to the same page. Existing checkout and upsell components must be preserved.
- `ghl_snapshot_diff_audit`: Compare a supplied snapshot export with this sub-account's live custom values, custom fields, tags and calendars. Include the snapshot ID and at least one asset category. The export is user-supplied; its ownership and freshness are unverified. Missing categories remain unverified. This does not overwrite assets.
- `ghl_user_role_governance`: Compare staff assigned to the connected sub-account with a selected permission preset. This audit does not change roles.
- `ghl_workflow_ivr_builder`: Preview a form-screening, intake, or call-menu workflow, then apply that preview. For multi-step-intake, provide formId and input.tags (one to ten existing tag IDs), input.taskTitle and input.taskBody. Draft creation and publication are separate requested actions.