How do I obtain an API token for InvGate?
In your InvGate Service Desk instance, go to **Settings > Integrations > API** (or ask your admin). The server authenticates via HTTP Basic with username `api` and the token as the password.
Invgate Service Desk MCP Server
@tracegazer
Basic information
About Invgate Service Desk MCP Server
MCP server for the InvGate Service Desk API — exposes InvGate Service Desk operations as Model Context Protocol tools.
Invgate Service Desk MCP Server config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"invgate-service-desk": {
"command": "uvx",
"args": [
"invgate-service-desk-mcp"
],
"env": {
"INVGATE_BASE_URL": "https://YOUR_INSTANCE.sd.cloud.invgate.net",
"INVGATE_API_TOKEN": "your-api-token",
"INVGATE_WRITE_PROFILE": "none"
}
}
}
}Invgate Service Desk MCP Server tools
Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
What is Invgate Service Desk?
A Model Context Protocol (MCP) server that gives AI assistants full access to an InvGate Service Desk or Service Management instance. It provides 96 tools across 11 domains for querying incidents, looking up users, searching the knowledge base, checking assets, and managing tickets through natural language. It is read‑only by default, with optional write operations behind explicit opt‑in.
How to use Invgate Service Desk?
Install via pip install invgate-service-desk-mcp or run with uvx invgate-service-desk-mcp. Configure with environment variables INVGATE_BASE_URL and INVGATE_API_TOKEN (and optionally INVGATE_WRITE_PROFILE), then add the server to claude_desktop_config.json. Alternatively, download the prebuilt .mcpb bundle and double‑click it for a one‑click installation.
Key features of Invgate Service Desk
- 96 tools across 11 domains (catalog, incidents, users, KB, etc.)
- Read‑only by default; write operations opt‑in via
INVGATE_WRITE_PROFILE - Supports STDIO and SSE/HTTP transports
- Optional OpenTelemetry observability for traces, metrics, and logs
- Prebuilt
.mcpbbundle for zero‑install setup - TOML configuration file for persistent settings
Use cases of Invgate Service Desk
- Query incidents and retrieve ticket details via natural language
- Look up users, groups, and asset information
- Search and browse the knowledge base
- Create, update, and reassign tickets (with write opt‑in)
- Log time entries and inspect automation triggers
Frequently asked questions
Can I enable write operations? How?
Yes. Set the environment variable `INVGATE_WRITE_PROFILE` to `support` (incidents + time tracking) or `full` (adds knowledge base writes). The legacy `INVGATE_ENABLE_WRITES=1` still works and maps to `full`. The default is `none` (read‑only).
What transports does the server support?
The default is STDIO, which keeps everything local. The `--transport sse` flag enables SSE/HTTP, but that transport has no built‑in authentication and should only be used bound to loopback or behind an authenticated reverse proxy.
Can I run the server without installing Python?
Yes. Download the prebuilt `.mcpb` bundle from the GitHub releases page or Smithery. Double‑click it to install in Claude Desktop – no Python, `npx`, or `uvx` required.
Is there a risk of data loss with write mode?
Write mode lets the connected agent create, modify, and delete real content. However, there is no API to delete a ticket – created tickets can only be cancelled, not removed.
More Other MCP servers
MCP Toolbox for Databases
googleapisMCP Toolbox for Databases is an open source MCP server for databases.
15.9K
Volley.sh
VolleyA good sequence diagram can solve almost any communication problem in engineering. Volley lets your agent write them as plain text, with the real request and response payloads on every arrow. It checks its own syntax wi
Hindsight
vectorize-ioHindsight: Agent Memory That Learns
50.4K
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
23.2K
Klarix Intelligence Engine
KlarixB2B competitive intelligence, live sales battlecards, 5-axis ICP prospect fit scoring, and tech stack teardowns over MCP and REST with cited public-web evidence.
Comments