Server data from the Official MCP Registry
MCP server for Kaseya VSA RMM — agents, patches, procedures, alarms, tickets.
MCP server for Kaseya VSA RMM — agents, patches, procedures, alarms, tickets.
The Kaseya VSA MCP server is a well-structured RMM integration tool with proper authentication and appropriate permission scoping for its purpose. Authentication is required and correctly handled through environment variables or gateway headers. The embedded UI bundle and dependency management are sound. Minor code quality issues around error handling and input validation do not substantially impact security. Supply chain analysis found 1 known vulnerability in dependencies (0 critical, 1 high severity).
3 files analyzed · 5 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Set these up before or after installing:
Environment variable: KASEYA_VSA_TENANT_URL
Environment variable: KASEYA_VSA_USERNAME
Environment variable: KASEYA_VSA_PASSWORD
Environment variable: KASEYA_VSA_K1_TOKEN
Environment variable: MCP_TRANSPORT
Environment variable: AUTH_MODE
Environment variable: LOG_LEVEL
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-wyre-technology-kaseya-vsa-mcp": {
"env": {
"AUTH_MODE": "your-auth-mode-here",
"LOG_LEVEL": "your-log-level-here",
"MCP_TRANSPORT": "your-mcp-transport-here",
"KASEYA_VSA_K1_TOKEN": "your-kaseya-vsa-k1-token-here",
"KASEYA_VSA_PASSWORD": "your-kaseya-vsa-password-here",
"KASEYA_VSA_USERNAME": "your-kaseya-vsa-username-here",
"KASEYA_VSA_TENANT_URL": "your-kaseya-vsa-tenant-url-here"
},
"args": [
"-y",
"@wyre-technology/kaseya-vsa-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
Model Context Protocol (MCP) server for the Kaseya VSA RMM API. Exposes managed endpoints, software / hardware inventory, patch state, agent procedures, alarms, Service Desk tickets, organizations, and machine groups to AI assistants.
| Tool | Description |
|---|---|
kaseya_vsa_list_agents | List managed endpoints (agents). Optional $filter. |
kaseya_vsa_get_agent | Get an agent's details by ID (renders as an interactive card in MCP Apps hosts). |
kaseya_vsa_get_software_inventory | Installed software for an agent. |
kaseya_vsa_get_hardware_inventory | Hardware audit for an agent. |
kaseya_vsa_get_patch_status | Pending and installed patches for an agent. |
kaseya_vsa_deploy_patches_now | Force a patch deploy on an agent (destructive — confirmation required). |
kaseya_vsa_list_procedures | Agent procedures available to run. |
kaseya_vsa_run_procedure | Execute a procedure on an agent (destructive — confirmation required). |
kaseya_vsa_list_alarms | Open alarms (optional state filter; date-window elicitation if missing). |
kaseya_vsa_list_tickets | Service Desk tickets (returns a friendly message if SD module isn't enabled). |
kaseya_vsa_list_organizations | Tenant organizations. |
kaseya_vsa_list_machine_groups | Machine group hierarchy. |
When the user omits required filters or runs a destructive action, the server uses MCP elicitation to prompt for choices or confirm.
kaseya_vsa_get_agent renders as a read-only interactive device card in MCP
Apps hosts (Claude Desktop/web), showing the endpoint's name, online status,
organization, machine group, OS, IP address, and last check-in. 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) applied at serve time. Plain-JSON behavior is unchanged in
other hosts. After editing ui/, regenerate the embedded bundle with
npm run build:ui.
| Variable | Required | Description |
|---|---|---|
KASEYA_VSA_TENANT_URL | yes | Full base URL incl. /api/v1.0 |
KASEYA_VSA_USERNAME | one of | Local-auth username |
KASEYA_VSA_PASSWORD | one of | Local-auth password (secret) |
KASEYA_VSA_K1_TOKEN | one of | Kaseya One SSO token (alternative to username + password) |
MCP_TRANSPORT | no | stdio (default) or http |
MCP_HTTP_PORT | no | HTTP listen port (default 8080) |
AUTH_MODE | no | env (default) or gateway |
Either the username + password pair OR the KASEYA_VSA_K1_TOKEN is required.
When deployed behind the WYRE MCP Gateway, set AUTH_MODE=gateway and the
server will read credentials from per-request HTTP headers:
X-Kaseya-VSA-Tenant-Url (required)X-Kaseya-VSA-Username (with password)X-Kaseya-VSA-Password (with username)X-Kaseya-VSA-K1-Token (alternative to username + password)Each request creates a fresh server instance with isolated credentials — no
cross-tenant process.env pollution.
npm install
npm run build
KASEYA_VSA_TENANT_URL=https://vsa.example.com/api/v1.0 \
KASEYA_VSA_USERNAME=... \
KASEYA_VSA_PASSWORD=... \
npm start
Run as HTTP for testing:
MCP_TRANSPORT=http npm start
curl http://localhost:8080/health
docker build -t kaseya-vsa-mcp .
docker run --rm -p 8080:8080 \
-e KASEYA_VSA_TENANT_URL=https://vsa.example.com/api/v1.0 \
-e KASEYA_VSA_USERNAME=... \
-e KASEYA_VSA_PASSWORD=... \
kaseya-vsa-mcp
Apache-2.0
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
by mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.