Deploy from the editor
“Deploy this branch and wait for the result” — right from Cursor, without switching to the panel.
- deploy_website
- wait_for_task
- restart_task
Core
ServersProvisioning in 5 minutes SitesWordPress, Laravel, PHP DeployOn push, with no downtime DatabasesMySQL, users, privileges DockerContainers alongside your sitesAI and automation
AI assistantManage your server in plain words MCP server80 tools for Claude and Cursor Operations centerEvery task step with logs Auto-tuningSettings tuned to your hardwareObservability
MonitoringMetrics, APM and alerts LogsNginx, PHP, MySQL, application BackupsTo your storage, encrypted ClustersServers and sites togetherSecurity and access
SecurityFirewall, Fail2Ban, isolation NetworkingInterfaces, DNS, diagnostics Web terminalCommands without an SSH client ConfigurationPHP, Nginx, MySQL from the panelManage servers from Claude and Cursor
Who it's for
WordPress2-click install, WP-CLI LaravelQueues, Horizon, Reverb For web agenciesAll clients in one panel For freelancersClient servers in one placeComparisons
Deploykin vs Laravel Forge Deploykin vs Ploi Deploykin vs RunCloud Deploykin vs ISPmanagerA running server connects as it is: the panel scans its packages, sites and databases. There is a separate wizard for Ploi.
How to connect a running serverClaude, Cursor or your own agent get 80 panel tools without a single SSH key. You decide what a token may do: which servers, what access level and for how long. Every call is audited.
Deploy main to prod and clear the config cache
website_statusHTTP 200 · nginx -t ok
read operate sudo databases have their own level
Use cases
80 tools: everything you do in the panel by hand is available to an agent. On the right — the chain of calls and the access level the token needs.
“Deploy this branch and wait for the result” — right from Cursor, without switching to the panel.
“Why 502?” — the assistant reads the logs and metrics itself and suggests a fix.
“Dump the database before the migration and show slow queries” — SQL without a console.
artisan, WP-CLI and arbitrary commands — as the site's user, with an audit trail.
“Connect this VPS, install the Laravel stack and create a site from the repository” — the agent starts provisioning and waits for it to finish.
Besides tools, the server ships two checklists — a safe deploy and a server diagnosis — plus a usage guide that tells the agent how to work with the panel.
Control
Between “the AI decided” and “it ran on the server” stand the token's level, its owner's role, the list of allowed tools and the dangerous command guard.
The agent needs no keys, passwords or server credentials. It gets an MCP token — and the panel performs every operation itself over its own secured connection. Revoke the token and access closes instantly, with no keys left on servers to clean up.
operatereadselect-onlyExpiry
A token's read and operate always work. Its sudo can be locked behind a security key: you open it from the token list for 15 minutes, an hour or eight, and it locks again when the time is up.
sudoreadoperateOpen sudo for
The level sets how deep a token can go; the tool list sets what exactly it can do. Disabled tools disappear from tools/list, so the agent never learns they exist.
Where the token works from
The activity log records every call — allowed or denied — with the token name and the reason for the denial. Denied calls trigger an alert to your subscribed channels.
Channels
Reads — metrics, logs, statuses — don't consume the limit: only mutating actions count.
Free of charge
list_servers
get_server
server_metrics
tail_log
db_query
read_env
website_status
wait_for_task
Quickstart
MCP is an open standard: one endpoint for everyone. The panel has step-by-step guides for claude.ai, Claude Desktop, Claude Code and Cursor — and a prompt that lets any other agent connect itself.
# claude.ai → Settings → Connectors # → Add custom connector https://app.deploykin.com/mcp # no token needed: sign in with OAuth # level follows your role, up to operate
"mcpServers": {
"deploykin": {
"url":
"https://app.deploykin.com/mcp",
"headers": {
"Authorization": "Bearer dk_mcp_x7Lq2Rv…" }
}
}
$ claude mcp add --transport http \
deploykin \
https://app.deploykin.com/mcp \
--header \ "Authorization: Bearer dk_mcp_…"
"mcpServers": {
"deploykin": {
"url":
"https://app.deploykin.com/mcp",
"headers": {
"Authorization": "Bearer dk_mcp_x7Lq2Rv…" }
}
}
Task manager
The agent does nothing “around” the panel: every action becomes a task in Deploykin's shared task manager — right next to your own deploys and operations.
FAQ
The protocol, the safety model and how the MCP server differs from the assistant in the panel — in short.
Model Context Protocol is an open standard that AI clients use to connect to external services. Deploykin runs an MCP server: any compatible client gets 80 panel tools — from deploys to SQL.
Really. The agent only sees an MCP token. The panel performs all operations over its own secured server connection, SQL runs under separate managed database users, and .env files and configs are served with secrets redacted.
The command never reaches the server: the dangerous command guard blocks destructive patterns — rm -rf /, mkfs, fork bombs, DROP DATABASE, UPDATE without WHERE — before execution. The critical protection tier cannot be turned off. And arbitrary commands are only available to a sudo-level token, which is issued with password confirmation and always has an expiry.
Today programmatic access to Deploykin is MCP: an open protocol over HTTP that works without AI too. If you specifically need classic REST — write to us and we'll share our plans.
The tools, access levels, guard and audit are the same. The assistant works right in the panel and in Telegram and shows an approval card before it changes anything. The MCP server exposes the same tools to external clients — Claude, Cursor and your own agents — where the token sets the boundaries.
In the panel 203.0.113.21 Connect done in 4 min 52 s
7 days free. An MCP token takes a minute to issue in the panel.
We use cookies and the Yandex Metrica web-analytics service (including Session Replay) to improve the site. Details are in the privacy policy.