# voice_ai_patch_agent Patch Agent Agent View of the PolicyLayer registry record for `voice_ai_patch_agent`. HTML page: https://policylayer.com/tools/aiwerk-mcp-server-ghl/voice-ai-patch-agent ## Facts - Tool: `voice_ai_patch_agent` - Server: Ghl (`@aiwerk/mcp-server-ghl`) — https://policylayer.com/tools/aiwerk-mcp-server-ghl.md - Install: `npx -y @aiwerk/mcp-server-ghl` - Homepage: https://www.npmjs.com/package/@aiwerk/mcp-server-ghl - Risk category: Write (Medium risk) - Registry record: grade F, identity unverified - Server rate-limited: no - Parameters: 12 (1 required) - Recommended policy verdict: Rate-limited ## Parameters | Parameter | Type | Required | Description | | --- | --- | --- | --- | | `agentId` | string | yes | Unique agent identifier | | `voiceId` | string | no | Identifier for the speech synthesis voice from available voice options. Default: Auto generated | | `language` | string | no | Language code for the agent's speech and understanding. Default: "en-US" | | `timezone` | string | no | IANA timezone identifier affecting working hours and scheduling. Default: Location timezone | | `agentName` | string | no | Display name for the voice AI agent, between 1-40 characters. Default: "My Agent {random 3 digit number}" | | `locationId` | string | no | Location ID Defaults to GHL_LOCATION_ID when omitted. | | `agentPrompt` | string | no | Custom instructions defining the agent's behavior and personality. Default: Basic prompt generated automatically | | `translation` | object | no | Language translation settings including enablement flag and target language code. Rules: (1) translation.enabled can only be true if the agent's language is not | | `businessName` | string | no | Name of the business this agent represents. Default: Uses location name | | `numberPoolId` | string | no | Identifier for the number pool managing phone number allocation. Default: null | | `inboundNumber` | string | no | Phone number for receiving inbound calls to this agent. Default: null | | `patienceLevel` | string | no | Tolerance level for caller response delays. Default: "high" | Parameters from the server's own tool schema. ## Example call (MCP tools/call, JSON-RPC 2.0) ```json { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "voice_ai_patch_agent", "arguments": { "agentId": "" } } } ``` ## Why voice_ai_patch_agent is rated Medium An AI agent can call voice_ai_patch_agent faster than any human can review: one bad instruction and it creates or modifies resources in Ghl by the hundred, each call as confident as the last. Risk signals: High parameter count (27 properties) ## Use case AI agents use voice_ai_patch_agent to create or update resources in Ghl, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ghl environment. ## Recommended policy (PolicyLayer) Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Ghl: ```json { "version": "1", "default": "deny", "tools": { "voice_ai_patch_agent": { "limits": [ { "counter": "voice_ai_patch_agent_rate", "window": "minute", "max": 30, "scope": "grant" } ] } } } ``` ## Other tools on Ghl (568) - `ad_manager_fb_delete_ad` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-ad.md - `ad_manager_fb_delete_ad_account` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-ad-account.md - `ad_manager_fb_delete_adset` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-adset.md - `ad_manager_fb_delete_campaign` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-campaign.md - `ad_manager_fb_delete_custom_audience` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-custom-audience.md - `ad_manager_fb_delete_integration` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-integration.md - `ad_manager_fb_delete_page` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-delete-page.md - `ad_manager_fb_remove_custom_audience_member` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-fb-remove-custom-audience-member.md - `ad_manager_google_delete_ad_account` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-google-delete-ad-account.md - `ad_manager_google_delete_conversion` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-google-delete-conversion.md - `ad_manager_google_delete_segment` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-google-delete-segment.md - `ad_manager_li_delete_ad_account` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/ad-manager-li-delete-ad-account.md - `agent_studio_delete_agent` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/agent-studio-delete-agent.md - `associations_delete_association` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/associations-delete-association.md - `associations_delete_relation` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/associations-delete-relation.md - `brand_boards_delete_brand_board` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/brand-boards-delete-brand-board.md - `businesses_delete_business` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/businesses-delete-business.md - `calendars_delete_appointment_note` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-appointment-note.md - `calendars_delete_calendar` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-calendar.md - `calendars_delete_calendar_resource` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-calendar-resource.md - `calendars_delete_event` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-event.md - `calendars_delete_event_notification` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-event-notification.md - `calendars_delete_group` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-group.md - `calendars_delete_schedule` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-delete-schedule.md - `calendars_remove_calendar_from_schedule` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/calendars-remove-calendar-from-schedule.md - `contacts_delete_contact` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/contacts-delete-contact.md - `contacts_delete_contact_from_workflow` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/contacts-delete-contact-from-workflow.md - `contacts_delete_note` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/contacts-delete-note.md - `contacts_delete_task` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/contacts-delete-task.md - `contacts_remove_contact_from_campaign` — Destructive — https://policylayer.com/tools/aiwerk-mcp-server-ghl/contacts-remove-contact-from-campaign.md - …and 538 more: https://policylayer.com/tools/aiwerk-mcp-server-ghl.md ## For agents This record is a snapshot. Live verdicts and the full registry: - Check every server in your MCP config at once: `npx -y policylayer stack` - Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md) - Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events` --- Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=aiwerk-mcp-server-ghl · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aiwerk-mcp-server-ghl