Install with your coding agent
If you work through a coding agent, it can install Xovris for you. It uses the same wizard and the same verify step as a person would, so the result is identical – and removal is just as exact. Add the Xovris server to your agent client:
Ships with the first release
Each coding agent gets its own one-line way to add Xovris – a command, a setting or a link – and signs you in from your browser the first time.
- Claude Code
- Codex
- Gemini CLI
- GitHub Copilot CLI
- VS Code
- Cursor
- LM Studio
- Goose
- Windsurf
- ChatGPT
- Claude
- Any MCP client
1. Add the Xovris server to your agent
Section titled “1. Add the Xovris server to your agent”Your agent client signs you in to Xovris in your browser the first time it connects. The command or setting for each client is in the box at the top of this page.
2. Paste this prompt
Section titled “2. Paste this prompt”Ships with the first release
Paste one prompt into your coding agent and it sets Xovris up for you: it shows you every change first and asks you to approve the sign-in.
Add Xovris monitoring to this project.
1. Call the xovris tool install_plan and show me the changes it lists before making any.
2. Run `npx xovris@latest init --yes` in the project folder. When it prints a sign-in link and code, ask me to approve it in my browser - never type a key yourself.
3. Once I have deployed, call run_verify with the connection id the wizard printed and tell me only what it reports.
If I ask to undo it, run `npx xovris@latest remove`.The agent shows you the changes before making them, runs the wizard, and asks you to approve the sign-in in your browser. It never handles a key: the wizard writes it straight into your git-ignored env file.
What the agent can do
Section titled “What the agent can do”The server gives the agent six tools, all of them reads. It can look at setup and connections, plan an install and check it, and read incidents and issues. Every tool reads; changes, repairs and deletions stay in the command centre, where you approve them.
| Tool | What it does |
|---|---|
setup_status |
The setup steps and each connection’s rungs, as stored |
install_plan |
The exact changes the wizard will make for a stack |
run_verify |
Reads a connection back – telemetry is reported only once an event is stored |
connection_list |
Every connection the token can see, with its health |
incident_get |
One incident with its evidence, repair and verification |
issue_list |
Error issues with their counts and releases |
Access can be limited to one project: such a token sees nothing outside it. Revoking the token in Connections stops it at once, and every call is recorded in the audit log.
Agent skill
Section titled “Agent skill”Agents that load skills can use the install-xovris skill. It follows the same steps.