kaseya-bms-mcp
MCP server for Kaseya BMS PSA — tickets, accounts, time entries, and contracts. Enables AI assistants to manage service desk operations via the Kaseya BMS API.
README
Kaseya BMS MCP Server
Model Context Protocol (MCP) server for the Kaseya BMS PSA API. Exposes tickets, accounts, contacts, contracts, time entries, the service catalog, and the knowledge base to AI assistants.
Tools
| Tool | Description |
|---|---|
kaseya_bms_list_tickets |
List tickets. Optional $filter; status pick if omitted. |
kaseya_bms_get_ticket |
Get a ticket by id. |
kaseya_bms_create_ticket |
Create a new ticket (destructive — confirmation required). |
kaseya_bms_add_ticket_note |
Append a note to a ticket (destructive — confirmation required). |
kaseya_bms_list_time_entries |
Time entries by date range (24h / 7d / 30d / custom / all). |
kaseya_bms_list_accounts |
Accounts (clients). |
kaseya_bms_list_contacts |
Contacts. |
kaseya_bms_list_contracts |
Contracts. |
kaseya_bms_list_service_catalog |
Service catalog items. |
kaseya_bms_search_knowledge_base |
Knowledge base search. |
When the user omits required filters or runs a destructive action, the server uses MCP elicitation to prompt for choices or confirm.
Configuration
Environment-variable mode (default)
| Variable | Required | Description |
|---|---|---|
KASEYA_BMS_TENANT_SUBDOMAIN |
yes | Tenant subdomain (e.g. yourcompany) |
KASEYA_BMS_API_TOKEN |
one of | BMS API token (secret) |
KASEYA_BMS_K1_TOKEN |
one of | Kaseya One SSO token (secret) |
MCP_TRANSPORT |
no | stdio (default) or http |
MCP_HTTP_PORT |
no | HTTP listen port (default 8080) |
AUTH_MODE |
no | env (default) or gateway |
Either KASEYA_BMS_API_TOKEN OR KASEYA_BMS_K1_TOKEN is required.
Gateway mode
When deployed behind the WYRE MCP Gateway, set AUTH_MODE=gateway and the
server will read credentials from per-request HTTP headers:
X-Kaseya-BMS-Tenant-Subdomain(required)X-Kaseya-BMS-API-Token(or)X-Kaseya-BMS-K1-Token
Each request creates a fresh server instance with isolated credentials — no
cross-tenant process.env pollution.
Local development
npm install
npm run build
KASEYA_BMS_TENANT_SUBDOMAIN=yourcompany \
KASEYA_BMS_API_TOKEN=... \
npm start
Run as HTTP for testing:
MCP_TRANSPORT=http npm start
curl http://localhost:8080/health
Docker
docker build -t kaseya-bms-mcp .
docker run --rm -p 8080:8080 \
-e KASEYA_BMS_TENANT_SUBDOMAIN=yourcompany \
-e KASEYA_BMS_API_TOKEN=... \
kaseya-bms-mcp
License
Apache-2.0
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.