Frontdesk AI
Officialby tersePrompts
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Model name for LiteLLM or OpenAI-compatible endpoint. | |
| ZAI_MODEL | No | Z.ai GLM model name (e.g., glm-5.3-flash). | glm-5.3-flash |
| NTFY_TOPIC | No | ntfy.sh topic for push notifications. Optional. | |
| A2A_ENABLED | No | Feature flag for the A2A agent. Defaults to enabled. | true |
| LLM_API_KEY | No | API key for LiteLLM or any OpenAI-compatible endpoint. Required along with LLM_BASE_URL if using this provider. | |
| MCP_ENABLED | No | Feature flag for the MCP server. Defaults to enabled. | true |
| ZAI_API_KEY | No | Z.ai GLM API key (legacy default). One of the LLM provider keys is required for the MCP server to run. | |
| LLM_BASE_URL | No | Base URL for LiteLLM or any OpenAI-compatible endpoint (e.g., https://your-proxy.example/v1). | |
| OPENAI_MODEL | No | OpenAI model name (e.g., gpt-4o). | gpt-4o |
| VERCEL_TOKEN | No | Vercel token used by deploy scripts. Not needed to run the MCP server. | |
| ASSISTANT_NAME | No | Title tag used in metadata. Not needed for MCP. | |
| OPENAI_API_KEY | No | OpenAI API key. One of the LLM provider keys is required for the MCP server to run. | |
| RESEND_API_KEY | No | Resend API key for the send_email tool. Optional; missing key disables the tool. | |
| ANTHROPIC_MODEL | No | Anthropic model name (e.g., claude-sonnet-4-5). | claude-sonnet-4-5 |
| ANTHROPIC_API_KEY | No | Anthropic Claude API key. One of the LLM provider keys is required for the MCP server to run. | |
| ASSISTANT_TAGLINE | No | Meta description. Not needed for MCP. | |
| VERCEL_PROJECT_ID | No | Vercel project ID used by deploy scripts. Not needed to run the MCP server. | |
| ASSISTANT_TIMEZONE | No | IANA timezone for availability display. Optional. | |
| NEXT_PUBLIC_GITHUB | No | GitHub URL shown in the header. Not needed for MCP. | |
| NEXT_PUBLIC_UPI_ID | No | UPI ID for 'Buy me a coffee' button. Empty hides the button. Not needed for MCP. | |
| ASSISTANT_EMAIL_FROM | No | Verified sender address for emails, e.g. 'Concierge <onboarding@resend.dev>'. Optional. | |
| NEXT_PUBLIC_LINKEDIN | No | LinkedIn URL shown in the header. Not needed for MCP. | |
| NEXT_PUBLIC_SITE_URL | No | Fallback origin for the copied agent set-up. Not needed for MCP. | |
| CALENDLY_ACCESS_TOKEN | No | Calendly Personal Access Token for the calendar tool. Optional; missing key disables the tool. | |
| ASSISTANT_INTERNAL_EMAIL | No | Inbox that the assistant emails messages and visit alerts to. Optional. | |
| NEXT_PUBLIC_CONTACT_EMAIL | No | Contact email shown in the header. Not needed for MCP. | |
| NEXT_PUBLIC_ASSISTANT_NAME | No | Header title for the chat UI. Not needed for MCP but part of app configuration. | |
| NEXT_PUBLIC_ASSISTANT_TAGLINE | No | Header tagline for the chat UI. Not needed for MCP but part of app configuration. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues