Skip the install. Get this working in under 2 minutes.
Start a free trial on cloud.anythingmcp.com, add the Matrix42 in one click, then point your AI client (Claude, ChatGPT, Copilot or Cursor) at the generated MCP endpoint. No Docker, no git clone, zero engineering experience required.
Summary
Matrix42 Enterprise Service Management: query any configuration item, incident, service request, asset or user with Matrix42's fragment query API. Bearer token minted from an API token against your own instance.
Try asking
Example prompts for Matrix42
Click any prompt to copy it. Paste into Claude, ChatGPT, Cursor, Gemini, Copilot or OpenClaw to run it against this connector.
Claude is AI and can make mistakes. Please double-check responses.
💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Matrix42, paste your credentials, mint an MCP API key — done. No Docker, no
git clone, no local server.
Matrix42 + Gemini
Matrix42 Enterprise Service Management: query any configuration item, incident, service request, asset or user with Matrix42's fragment query API. Bearer token minted from an API token against your own instance.
Prerequisites
See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:
MATRIX42_URL, MATRIX42_API_TOKEN
Step 1 — Get credentials
Setup
- In Matrix42 open Administration → Integration → API Tokens and create a token for a service account with the roles the agent needs. Matrix42 applies role-based access on top of the API, so a restricted account sees fewer fragments.
- Set
MATRIX42_URLto your instance root (e.g.https://esm.example.com/M42Services, no trailing slash) andMATRIX42_API_TOKENto the token. - The adapter exchanges that token for a short-lived bearer at
/api/ApiToken/Tokenand refreshes it automatically. AnythingMCP stores the bearer encrypted inconnector_auth_cache.
…(continued in the in-app connector instructions)
Step 2 — Install the adapter
curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d
Step 3 — Add the connector in Gemini
Gemini CLI reads MCP servers from ~/.gemini/settings.json (or %APPDATA%\gemini\settings.json on Windows). Add:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Get your MCP API key from AnythingMCP → Profile → MCP API Keys → New Key.
- Save the file and restart
gemini. - Run
/mcpinside the Gemini CLI —Matrix42should be listed as available. - Vertex AI Studio: pass
https://cloud.anythingmcp.com/mcpto thetoolsarray of your request with the same Bearer header.
Available tools
| Tool | What it does |
|---|---|
matrix42_query_fragments | Query any Matrix42 fragment by name with a column list and a SQL-flavoured where clause |
matrix42_get_fragment_schema | Read the column definitions of one fragment: the real column names, their types and their relations |
matrix42_query_incidents | Query incidents with a where clause over the incident fragment: state, priority, category, reported date and the affected user |
matrix42_query_service_requests | Query service requests with a where clause: their state, requested service, requester and fulfilment dates |
matrix42_query_assets | Query the asset base: hardware and software configuration items with their name, type, serial number, status and assigned user |
matrix42_query_users | Query the user base with their display name, e-mail, department and location |
matrix42_get_object | Read one configuration item by its object id, returning the named fragments attached to it |
FAQ
Does Gemini 1.5 Pro or 2.x support MCP? Yes — Gemini CLI ≥ 0.4 and Vertex AI tools API both accept MCP httpUrl connectors with Bearer headers.
Next steps
Was this guide helpful?
