HighLevel Agency & Builder MCP
Server Details
Review HighLevel changes. Built by Moosh Works (https://mooshworks.com).
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- mooshee/highlevel-agency-mcp
- GitHub Stars
- 0
- Server Listing
- HighLevel Agency & Builder MCP
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 13 tools
Most tools target clearly distinct domains (custom values, phone wallets, snapshots, user roles, domains, site builder, workflows), but three diagnostics tools — ghl_agency_connection_health, ghl_agency_contexts, and ghl_agency_doctor — all report on the connected sub-account and permission state with only subtle differences. An agent may struggle to pick the right one when it just wants to know 'is my connection working and what can I do'.
All tools share a consistent ghl_<domain>_<concept> snake_case pattern with a stable prefix, which is easy to scan and group. Minor deviation: some tools use an action suffix (tools_enable, tools_search, custom_values_audit) while others use a noun/builder suffix (doctor, contexts, workflow_ivr_builder), so verb placement is not uniform.
13 tools sits comfortably in the well-scoped range, and each tool maps to a distinct capability area (diagnostics, audits, builder preview/apply operations). No tool looks like a redundant duplicate of another beyond the diagnostics trio, which is a granularity issue rather than bloat.
The surface covers a good spread of read/audit and preview-apply workflows, but several audits are dead ends with no remediation counterpart (custom value fixes, phone routing fixes), and there are no tools for listing or editing core assets like calendars, custom fields, tags, or contacts outside the snapshot diff. Agents will hit gaps after diagnosing a problem.
Available Tools
13 toolsghl_agency_connection_healthCheck the HighLevel connectionCRead-onlyIdempotentInspect
Check access to the connected sub-account and whether builder access is available.
Inputs: includeDoctor.
ghl_agency_contextsShow the connected accountARead-onlyIdempotentInspect
Show the sub-account selected during connection. Connect again to choose a different sub-account.
Inputs: no named parameters.
ghl_agency_doctorCheck account accessBRead-onlyIdempotentInspect
Check the connected account and access to custom values, calendars, and workflows. Report unavailable permissions separately.
Inputs: no named parameters.
ghl_agency_locationsInspect the connected sub-accountBRead-onlyIdempotentInspect
Read the location profile, timezone and configuration for the connected sub-account.
Inputs: location.
ghl_agency_tools_enableSet the change policyCInspect
Choose read-only access or allow changes after a preview. Every change still requires dryRun=false and the returned preview ID.
Inputs: policyPreset (required).
ghl_agency_tools_searchFind tools and workflow templatesCRead-onlyIdempotentInspect
Find tools and workflow templates by keyword or category.
Inputs: query, category.
ghl_custom_values_auditCheck custom values and merge tagsBRead-onlyIdempotentInspect
Find blank custom values, unresolved placeholders, and broken references in the connected sub-account's message templates. Optional supplied templates are checked too.
Inputs: templates, locationId.
ghl_domain_ssl_onboardSave and check a site domainBDestructiveInspect
Preview and save a domain record and funnel binding. Report DNS and HTTPS readiness separately. Hosting attachment, page routing and publication require separate steps.
Inputs: domain (required), funnelId (required), dryRun, stepId, +2 more.
ghl_phone_wallet_auditCheck phone routing and number poolsBRead-onlyIdempotentInspect
Inspect connected-account phone numbers, number pools, missing routing, and forwarding loops. Routing risks do not establish charges or savings.
Inputs: locationId.
ghl_site_builder_syncPreview or apply a page changeBDestructiveInspect
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.
Inputs: stepId (required), funnelId (required), mode, input, +3 more.
ghl_snapshot_diff_auditCompare a sub-account with a snapshot exportARead-onlyIdempotentInspect
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.
Inputs: snapshotId (required), snapshotExport (required), locationId.
ghl_user_role_governanceCheck staff permissionsBRead-onlyIdempotentInspect
Compare staff assigned to the connected sub-account with a selected permission preset. This audit does not change roles.
Inputs: preset (required), locationId.
ghl_workflow_ivr_builderBuild a workflow or call menuBDestructiveInspect
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.
Inputs: name (required), preset (required), input, phone, +9 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Automate GoHighLevel across CRM, messaging, calendars, marketing, e-commerce, and billing. Manage…
Preview form screening and manage site rules. Built by Moosh Works (https://mooshworks.com).
Full-stack GoHighLevel (GHL) MCP for funnels, client DNS/SSL, LeadShield spam blockers & snapshots.
Full-stack GoHighLevel (GHL) MCP for funnels, client DNS/SSL, LeadShield spam blockers & snapshots.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceLets Claude Code read in-browser review comments, element removals, and text/CSS edits made on localhost dev pages, complete with selectors, HTML, React component names, source files, and screenshots. It also lets the agent claim tasks as in progress and submit solutions for the user to accept or reopen.105 npm1MIT
- AlicenseAqualityCmaintenanceThe open-source review layer for AI agents. Work done for humans is decided by humans.1810 npm1AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceLets AI agents read frame-accurate video review notes — timestamps, frames, annotations, and pointing targets tied to source elements — so they can fix rendered videos and re-check the results. Supports listing reviews, retrieving annotated frames, watching for new feedback, acknowledging, replying, resolving, dismissing, and leaving their own critique notes.13 npm3MIT
- AlicenseBqualityBmaintenanceHelps teams standardize implementation quality with project-aware rules, code review, health scoring, and an active agent workflow for intake, planning, verification, and release.16GPL 3.0
Glama MCP Gateway
Add one secure layer between your agents and this server.