MCP server for Syncro MSP — tickets, assets, contacts, invoices, and RMM tools for AI assistants
- ✓Open-source license (Apache-2.0)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add syncro-mcp -- npx -y github{
"mcpServers": {
"syncro-mcp": {
"command": "npx",
"args": ["-y", "github"],
"env": {
"SYNCRO_API_KEY": "<syncro_api_key>"
}
}
}
}SYNCRO_API_KEYResumen de MCP Servers
# Syncro MCP Server
A Model Context Protocol (MCP) server for Syncro MSP, implementing a decision tree architecture for efficient tool navigation.
## One-Click Deployment
[](https://cloud.digitalocean.com/apps/new?repo=https://github.com/WYRE-AI/syncro-mcp/tree/main)
[](https://deploy.workers.cloudflare.com/?url=https://github.com/WYRE-AI/syncro-mcp)
> **Operator note — GitHub Packages authentication (required for one-click deploys).**
> This server depends on the private `@wyre-technology/node-syncro` SDK, which is
> hosted on **GitHub Packages**. GitHub Packages requires an authentication token
> on every install (no anonymous reads, even for public packages), so the cloud
> builders fail during `npm install` with `401 Unauthorized` unless you supply a
> token. Create a GitHub **Personal Access Token** with the `read:packages` scope
> and provide it to the builder:
>
> - **Cloudflare Workers** — set a build/environment variable named `NODE_AUTH_TOKEN` to your PAT.
> - **DigitalOcean App Platform** — set a **build-time** secret named `GITHUB_TOKEN` to your PAT.
>
> For local `npm install`, run `export NODE_AUTH_TOKEN=$(gh auth token)` first.
## Features
- **Decision Tree Architecture**: Tools are organized by domain and loaded lazily
- **Domain Navigation**: Navigate between customers, tickets, assets, contacts, and invoices
- **Lazy Loading**: Domain handlers and the Syncro client are loaded on-demand
- **Full Syncro API Coverage**: Access to key Syncro MSP functionality
- **Interactive Ticket Card (MCP Apps)**: `syncro_tickets_get` renders as an interactive card in MCP Apps hosts (Claude Desktop/web) with an in-card "Add comment" round-trip via `syncro_tickets_add_comment` (internal-only by default); plain-JSON behavior is unchanged in other hosts. The card is neutral by default, brandable via `window.__BRAND__` injection or `MCP_BRAND_*` env vars (`MCP_BRAND_NAME`, `MCP_BRAND_LOGO_URL`, `MCP_BRAND_PRIMARY_COLOR`, `MCP_BRAND_ACCENT_COLOR`, `MCP_BRAND_BG`, `MCP_BRAND_TEXT`) — no rebuild needed.
## Installation
> WYRE MCP servers are distributed via OCI/GHCR images and (where available) MCPB bundles. The npm package `@wyre-ai/syncro-mcp` is also published to **GitHub Packages** (`npm.pkg.github.com`); installing it requires an authenticated `.npmrc` with `read:packages` scope (run `export NODE_AUTH_TOKEN=$(gh auth token)` locally).
### Option 1: WYRE MCP Gateway (Recommended)
Use the hosted gateway at [mcp.wyre.ai](https://mcp.wyre.ai) — paste your Syncro API key into the gateway UI and you're done.
```json
{
"mcpServers": {
"syncro": {
"type": "http",
"url": "https://mcp.wyre.ai/v1/syncro/mcp",
"headers": {
"X-Syncro-Api-Key": "${SYNCRO_API_KEY}"
}
}
}
}
```
### Option 2: Claude Code CLI (run from GitHub)
```bash
claude mcp add syncro \
-e SYNCRO_API_KEY=your-api-key \
-e SYNCRO_SUBDOMAIN=your-subdomain \
-- npx -y github:WYRE-AI/syncro-mcp
```
### Option 3: Docker (GHCR)
```bash
docker run --rm \
-e SYNCRO_API_KEY=your-api-key \
-e SYNCRO_SUBDOMAIN=your-subdomain \
ghcr.io/wyre-ai/syncro-mcp:latest
```
### Option 4: From Source
```bash
git clone https://github.com/WYRE-AI/syncro-mcp.git
cd syncro-mcp
npm ci
npm run build
node dist/index.js
```
## Configuration
Set the following environment variables:
| Variable | Required | Description |
|----------|----------|-------------|
| `SYNCRO_API_KEY` | Yes | Your Syncro API key |
| `SYNCRO_SUBDOMAIN` | No | Your Syncro subdomain (if applicable) |
### Getting Your API Key
1. Log in to your Syncro MSP account
2. Navigate to Settings > API Tokens
3. Generate a new API token with appropriate permissions
## Architecture
### Decision Tree Navigation
The server uses a hierarchical approach to tool discovery:
1. **Initial State**: Only navigation and status tools are exposed
2. **After Navigation**: Domain-specific tools become available
3. **Back Navigation**: Return to the main menu to switch domains
This reduces cognitive load and improves LLM tool selection accuracy.
### Available Domains
| Domain | Description | Tools |
|--------|-------------|-------|
| `customers` | Manage customer accounts | list, get, create, search |
| `tickets` | Manage support tickets | list, get, create, update, add_comment |
| `assets` | Manage configuration items | list, get, search |
| `contacts` | Manage customer contacts | list, get, create |
| `invoices` | View and manage billing | list, get, create, email |
## Tools Reference
### Navigation Tools
#### syncro_navigate
Navigate to a domain to access its tools.
```json
{
"domain": "customers" | "tickets" | "assets" | "contacts" | "invoices"
}
```
#### syncro_back
Return to the main menu from any domain.
#### syncro_status
Show current navigation state and credential status.
### Customers Domain
#### syncro_customers_list
List customers with optional filters.
```json
{
"query": "search term",
"business_name": "Company Inc",
"email": "contact@example.com",
"include_disabled": false,
"page": 1,
"per_page": 25
}
```
#### syncro_customers_get
Get a specific customer by ID.
```json
{
"customer_id": 123
}
```
#### syncro_customers_create
Create a new customer.
```json
{
"business_name": "Acme Corp",
"firstname": "John",
"lastname": "Doe",
"email": "john@acme.com"
}
```
#### syncro_customers_search
Search customers by query string.
```json
{
"query": "acme",
"limit": 25
}
```
### Tickets Domain
#### syncro_tickets_list
List tickets with optional filters.
```json
{
"customer_id": 123,
"status": "Open",
"user_id": 456,
"resolved": false
}
```
#### syncro_tickets_get
Get a specific ticket by ID.
```json
{
"ticket_id": 789
}
```
#### syncro_tickets_create
Create a new ticket.
```json
{
"customer_id": 123,
"subject": "Network Issue",
"problem_type": "Network",
"comment_body": "Initial description"
}
```
#### syncro_tickets_update
Update an existing ticket.
```json
{
"ticket_id": 789,
"status": "Resolved",
"user_id": 456
}
```
#### syncro_tickets_add_comment
Add a comment to a ticket.
```json
{
"ticket_id": 789,
"body": "Comment text",
"hidden": false
}
```
### Assets Domain
#### syncro_assets_list
List assets with optional filters.
```json
{
"customer_id": 123,
"asset_type": "Desktop"
}
```
#### syncro_assets_get
Get a specific asset by ID.
```json
{
"asset_id": 456
}
```
#### syncro_assets_search
Search assets by query or serial number.
```json
{
"query": "workstation",
"asset_serial": "SN12345"
}
```
### Contacts Domain
#### syncro_contacts_list
List contacts with optional filters.
```json
{
"customer_id": 123,
"query": "john"
}
```
#### syncro_contacts_get
Get a specific contact by ID.
```json
{
"contact_id": 789
}
```
#### syncro_contacts_create
Create a new contact.
```json
{
"customer_id": 123,
"name": "Jane Smith",
"email": "jane@example.com"
}
```
### Invoices Domain
#### syncro_invoices_list
List invoices with optional filters.
```json
{
"customer_id": 123,
"status": "sent",
"since_date": "2024-01-01"
}
```
#### syncro_invoices_get
Get a specific invoice by ID.
```json
{
"invoice_id": 456
}
```
#### syncro_invoices_create
Create a new invoice.
```json
{
"customer_id": 123,
"due_date": "2024-02-01"
}
```
#### syncro_invoices_email
Email an invoice to the customer.
```json
{
"invoice_id": 456,
"subject": "Your Invoice"
}
```
## Rate Limiting
Syncro API has a rate limit of 180 requests per minute. The underlying `@wyre-technology/node-syncro` library handles rate limiting automatically.
## Development
```bash
# Install dependencies. The @wyre-technology/node-syncro SDK lives on GitHub
# Packages, so authenticate first:
export NODE_AUTH_TOKEN=$(gh auth token)
npm install
# Build
npm run build
# Run in development
npm run dev
# Type check
npm run typecheck
# Lint
npm run lint
```
## License
Apache-2.0
Lo que la gente pregunta sobre syncro-mcp
¿Qué es WYRE-AI/syncro-mcp?
+
WYRE-AI/syncro-mcp es mcp servers para el ecosistema de Claude AI. MCP server for Syncro MSP — tickets, assets, contacts, invoices, and RMM tools for AI assistants Tiene 3 estrellas en GitHub y su última actualización registrada es del 2026-08-26.
¿Cómo se instala syncro-mcp?
+
Puedes instalar syncro-mcp clonando el repositorio (https://github.com/WYRE-AI/syncro-mcp) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.
¿Es seguro usar WYRE-AI/syncro-mcp?
+
Nuestro agente de seguridad ha analizado WYRE-AI/syncro-mcp y le ha asignado un Trust Score de 95/100 (tier: Verified). Revisa el desglose completo de comprobaciones superadas y flags en esta página.
¿Quién mantiene WYRE-AI/syncro-mcp?
+
WYRE-AI/syncro-mcp es mantenido por WYRE-AI. La última actividad registrada en GitHub es del 2026-08-26, con 3 issues abiertos.
¿Hay alternativas a syncro-mcp?
+
Sí. En ClaudeWave puedes explorar mcp servers similares en /categories/mcp, ordenados por popularidad o actividad reciente.
Despliega syncro-mcp en tu cloud
Lleva este repo a producción en minutos. Cada plataforma genera su propio entorno con variables de entorno editables.
¿Mantienes este repo? Añade un badge a tu README
Pega el badge en tu README de GitHub para mostrar que está auditado por ClaudeWave. Cada badge enlaza de vuelta a esta página y muestra el Trust Score actual.
[](https://claudewave.com/repo/wyre-ai-syncro-mcp)<a href="https://claudewave.com/repo/wyre-ai-syncro-mcp"><img src="https://claudewave.com/api/badge/wyre-ai-syncro-mcp" alt="Featured on ClaudeWave: WYRE-AI/syncro-mcp" width="320" height="64" /></a>Más MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
The fastest path to AI-powered full stack observability, even for lean teams.
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!