Triggers automated workflows via webhooks for maintenance status changes and vendor escalations, allowing for extended automation such as emailing vendors or generating reports.
Connects to the Twilio API to facilitate sending WhatsApp notifications to tenants, supporting features like ticket acknowledgment and scheduling updates.
Provides capabilities to send automated tenant updates and maintenance notifications via WhatsApp using various message templates for acknowledgments, delays, and resolutions.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP PropTech Escalate the leaking water heater in unit 4C to a plumber and notify the tenant"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A production-ready Model Context Protocol (MCP) server that lets a Claude-powered agent orchestrate your full property maintenance workflow — built on top of an existing n8n + WhatsApp automation system.
┌─────────────────────────────────────────────────────────┐
│ Claude Agent / Desktop │
└────────────────────────┬────────────────────────────────┘
│ MCP (stdio / SSE)
┌────────────────────────▼────────────────────────────────┐
│ MCP PropTech Maintenance Server │
│ │
│ get_open_tickets update_maintenance_status │
│ notify_tenant escalate_to_vendor │
└──────┬──────────────────────────────────┬───────────────┘
│ │
┌──────▼──────┐ ┌────────▼──────────┐
│ Ticket DB │ │ Integrations │
│ (in-memory │ │ ┌─────────────┐ │
│ → Postgres │ │ │ n8n │ │
│ in prod) │ │ │ Webhooks │ │
└─────────────┘ │ ├─────────────┤ │
│ │ Twilio │ │
│ │ WhatsApp │ │
│ └─────────────┘ │
└───────────────────┘Tool | Description |
| Query tickets filtered by status, priority, category, property |
| Drive tickets through the lifecycle with audit notes |
| Send WhatsApp messages via 5 templates (acknowledgement, scheduled, update, resolved, delay) |
| Assign vendor, trigger n8n workflow, notify tenant in one call |
Related MCP server: n8n MCP Server
# 1. Install dependencies
npm install
# 2. Configure environment
cp .env.example .env
# Fill in ANTHROPIC_API_KEY, Twilio creds, n8n webhook URLs
# 3. Run the agent (single pass over the ticket queue)
npm run agent
# 4. Run as a daemon (checks every 5 minutes)
npm run agent:dev -- --daemonAdd this to your claude_desktop_config.json:
{
"mcpServers": {
"proptech-maintenance": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/MCPPropTech/src/mcp-server/index.ts"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-...",
"TWILIO_ACCOUNT_SID": "AC...",
"TWILIO_AUTH_TOKEN": "...",
"TWILIO_WHATSAPP_FROM": "whatsapp:+14155238886",
"N8N_WEBHOOK_MAINTENANCE": "https://your-n8n.com/webhook/maintenance",
"N8N_WEBHOOK_ESCALATE": "https://your-n8n.com/webhook/escalate"
}
}
}
}Then from Claude Desktop you can say things like:
"Show me all open emergency tickets"
"Escalate the burst pipe in unit 3B to a plumber"
"Send Marcus in 7A a WhatsApp update on his AC ticket"
src/mcp-server/)The server runs over stdio (for Claude Desktop / agent SDK) and exposes the
four tools above. Swap StdioServerTransport for SSEServerTransport to serve
over HTTP for remote deployments.
src/data/)An in-memory store with 6 seed tickets covering every status and priority.
Replace TicketStore internals with a Postgres/Supabase/Airtable adapter for
production — the tool handlers only call the store interface.
src/integrations/n8n.ts)Fires webhooks to two n8n endpoints:
Maintenance webhook — on every status change and tenant notification
Escalation webhook — when a vendor is assigned
Your n8n workflows handle the rest: emailing vendors, updating spreadsheets, creating calendar invites, sending owner reports.
src/integrations/whatsapp.ts)Uses the Twilio API to send WhatsApp messages. Gracefully falls back to simulation mode (console logging) when credentials are not set — perfect for demos and local development.
src/agent/maintenance-agent.ts)A full agentic loop using @anthropic-ai/sdk that:
Connects to the MCP server via StdioClientTransport
Fetches available tools and converts them to the Anthropic tool format
Runs an agentic loop until Claude stops calling tools
Logs each tool call and result to the console
open ──→ in_progress ──→ resolved ──→ closed
│ │ ↑
│ └──→ awaiting_tenant
│ │
└──→ escalated ←────┘
│
└──→ in_progress / resolvedVariable | Required | Description |
| Agent only | Claude API key |
| Optional | Twilio account SID for WhatsApp |
| Optional | Twilio auth token |
| Optional | Sender WhatsApp number |
| Optional | n8n status-change webhook URL |
| Optional | n8n vendor escalation webhook URL |
| Optional | n8n API key (if required by your instance) |
| Optional | JSON map overriding default vendor directory |
| Optional | Daemon poll interval (default: 300000 = 5 min) |
Escalates a maintenance ticket to a specialist vendor. Selects the right vendor from the directory based on trade (plumbing, electrical, hvac, etc.), updates ticket status to 'escalated', triggers an n8n workflow that emails/WhatsApps the vendor, and sends the tenant an update message. Use overrideVendorPhone to assign a specific vendor instead of the default.
| Name | Required | Description | Default |
|---|---|---|---|
| ticketId | Yes | The ID of the ticket to escalate. | |
| trade | Yes | The trade/specialty required. Used to select the appropriate vendor from the directory. | |
| urgencyNote | Yes | A clear description of why this is being escalated and any access/safety considerations the vendor needs to know. This is sent directly to the vendor. | |
| preferredTime | No | Human-readable preferred scheduling window, e.g. 'Tuesday afternoon' or 'ASAP — emergency'. Passed to the vendor via the n8n workflow. | |
| overrideVendorPhone | No | WhatsApp-formatted phone number (e.g. 'whatsapp:+15125550001') to use instead of the default vendor for this trade. Useful for one-off vendor assignments. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It does well by describing the multi-step process (updates ticket status, triggers workflow, sends messages) and the override capability. However, it doesn't mention potential side effects like whether this action is reversible, permission requirements, rate limits, or error handling for invalid inputs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized with two sentences that efficiently cover the tool's purpose and key functionality. The first sentence front-loads the main action and process steps, while the second focuses on an important parameter nuance. No wasted words, though it could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 5-parameter mutation tool with no annotations and no output schema, the description provides good coverage of the action and process. However, it lacks information about return values, error conditions, or system constraints. Given the complexity of the operation (multiple side effects), more behavioral context would be beneficial.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly. The description adds some context about trade selection ('based on trade') and the overrideVendorPhone use case ('assign a specific vendor instead of the default'), but doesn't provide additional semantic meaning beyond what's in the schema descriptions. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('escalates a maintenance ticket to a specialist vendor') and distinguishes it from siblings like 'get_open_tickets' (read-only), 'notify_tenant' (notification only), and 'update_maintenance_status' (status update only). It explicitly mentions the multi-step process including vendor selection, status update, workflow triggering, and tenant notification.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool ('escalates a maintenance ticket to a specialist vendor') and mentions the overrideVendorPhone parameter for specific assignments. However, it doesn't explicitly state when NOT to use it or name alternatives among the sibling tools (e.g., when to use update_maintenance_status instead).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieves maintenance tickets from the property management system. Filters by status (default: all non-resolved), priority, category, and property. Returns tickets sorted by priority (emergency first) then recency.
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | Filter by ticket status. Omit to return all non-resolved/non-closed tickets. | |
| priority | No | Filter to a specific priority level. | |
| category | No | Filter by maintenance category / trade. | |
| propertyId | No | Filter to tickets for a specific property (use property ID). | |
| limit | No | Maximum number of tickets to return (default: all matching). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It effectively describes key behaviors: default filtering (non-resolved tickets), sorting logic (priority then recency), and that it's a retrieval operation. However, it doesn't mention potential limitations like pagination, rate limits, or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences that efficiently cover purpose, filtering parameters, defaults, and sorting logic with zero wasted words. The description is appropriately sized and front-loaded with the core functionality.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only query tool with comprehensive schema documentation but no output schema, the description provides good context about filtering defaults and sorting behavior. It could be more complete by describing the return format or result structure, but given the tool's relative simplicity and good parameter documentation, it's mostly adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema - it mentions filtering by the same parameters but doesn't provide additional semantic context. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Retrieves maintenance tickets'), resource ('from the property management system'), and scope ('Filters by status, priority, category, and property'). It distinguishes from siblings like 'escalate_to_vendor' or 'update_maintenance_status' by being a read-only query tool rather than a mutation tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage context through filtering parameters and default behavior, but doesn't explicitly state when to use this tool versus alternatives like 'update_maintenance_status' for modifying tickets or 'notify_tenant' for communication. No explicit when-not-to-use guidance or prerequisite information is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sends a WhatsApp message to the tenant associated with a ticket. Supports five message templates: acknowledgement, scheduled, update, resolved, delay. Pass customMessage to override the template. Falls back to SMS if WhatsApp fails. Logs the notification to n8n and appends to ticket internal notes.
| Name | Required | Description | Default |
|---|---|---|---|
| ticketId | Yes | The ID of the ticket whose tenant should be notified. | |
| messageType | Yes | Template to use: acknowledgement — ticket received, being reviewed scheduled — repair booked, include scheduledFor date update — general progress note resolved — work complete delay — work delayed, reason explained | |
| customMessage | No | Optional custom message body. When provided, overrides the built-in template. Useful for specific instructions or unusual situations. | |
| scheduledFor | No | ISO 8601 datetime — required when messageType is 'scheduled'. The template will format this into a human-readable date/time for the tenant. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does well by disclosing key behavioral traits: it specifies the five message templates, fallback to SMS, and side effects (logs to n8n and appends to ticket internal notes). However, it doesn't mention potential rate limits, authentication needs, or error handling details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in three sentences: the first states the core action and templates, the second explains parameter behavior, and the third covers fallback and side effects. Every sentence adds essential information with zero wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description provides strong context about behavior, parameters, and side effects. It could be more complete by detailing the exact format of logged messages or clarifying error responses, but it covers the essential operational aspects well given the complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing detailed parameter documentation. The description adds some value by explaining the purpose of customMessage ('overrides the built-in template') and listing the five template types, but doesn't significantly enhance the schema's already comprehensive parameter semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the specific action ('Sends a WhatsApp message') and target resource ('to the tenant associated with a ticket'), distinguishing it from sibling tools like escalate_to_vendor or update_maintenance_status by focusing on tenant communication rather than vendor escalation or status updates.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (sending notifications to tenants about ticket updates) and mentions fallback behavior (SMS if WhatsApp fails), but does not explicitly state when not to use it or directly compare it to alternatives like escalate_to_vendor for vendor-related communications.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Updates the status of a maintenance ticket and records a history note. Fires an n8n webhook so your automation system stays in sync. Valid transitions: open→in_progress|awaiting_tenant|escalated, in_progress→awaiting_tenant|resolved|escalated, awaiting_tenant→in_progress|resolved|closed, escalated→in_progress|resolved, resolved→closed.
| Name | Required | Description | Default |
|---|---|---|---|
| ticketId | Yes | The ID of the ticket to update (e.g. 'ticket_001'). | |
| newStatus | Yes | The target status to transition the ticket into. | |
| note | Yes | A human-readable note explaining why this status change is being made. This is stored in the ticket history and may be relayed to the tenant. | |
| updatedBy | No | Name / identifier of whoever is making this change. | Claude MCP Agent |
| scheduledFor | No | ISO 8601 datetime — required when newStatus is 'in_progress' to record when the repair/visit is booked for. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: it's a mutation tool (implied by 'Updates'), records history notes, fires webhooks for automation sync, and enforces status transition rules. However, it doesn't mention potential side effects like error handling or permission requirements, leaving some gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with core functionality in the first sentence, followed by essential details in a logical flow. Every sentence earns its place: the first explains the primary action, the second adds automation context, and the third provides critical transition rules—all without waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description does well by covering purpose, usage rules, and behavioral context like webhook firing. It lacks details on return values or error responses, but given the schema's completeness and the description's focus on transitions and automation, it's largely sufficient for agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal value beyond the schema by implying parameter interactions (e.g., 'scheduledFor' is contextually linked to 'in_progress' status), but doesn't provide additional syntax or format details. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('Updates the status', 'records a history note', 'Fires an n8n webhook') and resources ('maintenance ticket', 'automation system'). It distinguishes itself from siblings like 'get_open_tickets' (read-only) and 'notify_tenant' (communication-focused) by emphasizing status transitions and system synchronization.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance by detailing valid status transitions (e.g., 'open→in_progress|awaiting_tenant|escalated'), which tells the agent when to use this tool versus alternatives. It implicitly suggests not using it for invalid transitions, though it doesn't name specific sibling alternatives for edge cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0escalate_to_vendorget_open_ticketsnotify_tenantupdate_maintenance_statusEach tool has a clearly distinct purpose with no overlap: escalate_to_vendor handles vendor escalation, get_open_tickets retrieves ticket data, notify_tenant sends tenant notifications, and update_maintenance_status updates ticket status. The descriptions specify unique actions and contexts, making misselection unlikely.
All tool names follow a consistent verb_noun pattern (e.g., escalate_to_vendor, get_open_tickets) using snake_case throughout. This predictable naming scheme enhances readability and agent usability without any deviations or mixed conventions.
With 4 tools, the count is reasonable for a property tech maintenance domain, covering key operations like retrieval, status updates, notifications, and escalations. It's slightly lean but well-scoped, as each tool serves a distinct function without redundancy.
The tool set covers core maintenance workflows: retrieving tickets, updating statuses, notifying tenants, and escalating to vendors. Minor gaps exist, such as no tool for creating new tickets or managing vendor directories, but agents can likely work around these with the provided tools.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Property management AI: work orders, vendors, appliances, and triage for Claude and ChatGPT.
Property maintenance triage and vendor packet generator.
Give your AI agents the tools to build, manage, and run automation workflows.
WhatsApp CRM for AI agents: search contacts, read chats, manage the sales pipeline, send messages.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/utkarsh-portfolio/MCPPropTech'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
