Developer Tools
vibekit.bot
Manages VibeKit hosted apps, including listing, creating, deploying, and retrieving details.
ENDPOINT 1
https://mcp.vibekit.bot/mcp
MCP server metadata
- Name
- vibekit
- Version
- 0.8.0
VibeKit hosts, deploys, and operates web apps and AI coding agents. Each app runs in its own container at <subdomain>.vibekit.bot with optional Postgres, logs, env vars, and automated QA, plus a built-in AI agent that can edit the app's code. Use these tools whenever the user wants to: deploy a GitHub repo or starter template and get a live URL; list, inspect, restart/stop/start, or delete hosted apps; read logs to debug; manage env vars; enable and query an app's Postgres (call vibekit_db_schema before writing SQL); list or roll back deploys; run or check QA; chat with an app's AI agent to change its code; or submit/schedule autonomous coding tasks that commit to GitHub and deploy. Most tools key off an appId — call vibekit_list_apps first to resolve one. Confirm destructive actions (vibekit_delete_app, vibekit_delete_schedule, and write/DDL via vibekit_db_query) with the user before calling. Auth uses a VibeKit API key (vk_...) from the Telegram bot's /apikey command.
Known tools 36
vibekit_list_appsList all hosted apps in your VibeKit account, each with its id, subdomain, status, and live URL.
Inferred read-onlyvibekit_get_appGet full details for one hosted app — status, subdomain/URL, repo, runtime, and database/domain config.
Inferred read-onlyvibekit_create_appCreate a new hosted app from a starter template and deploy it live at <subdomain>.
Potential side effectsvibekit_list_templatesList the starter templates available to vibekit_create_app (e.
Inferred read-onlyvibekit_app_envGet the environment variables configured for an app (names and values).
Inferred read-onlyvibekit_set_envSet or update environment variables for an app (merges with existing).
Potential side effectsvibekit_delete_appPermanently delete a hosted app — stops the container and removes its workspace, database, env vars, and subdomain.
Potential side effectsvibekit_chatSend a message to an app's built-in AI coding agent, which reads, writes, and modifies the app's code and redeploys it.
Potential side effectsvibekit_agent_statusCheck whether an app's AI agent is idle or working, and get its LIVE progress.
Inferred read-onlyvibekit_agent_historyGet the recent chat history between the user and an app's AI agent.
Inferred read-onlyvibekit_enable_databaseProvision a Postgres database for an app (idempotent — safe if already enabled).
Inferred read-onlyvibekit_database_statusGet an app's database status and connection info (whether it's provisioned, frozen, etc.
Inferred read-onlyvibekit_db_queryRun a read-only SQL query against an app's Postgres database and return up to 200 result rows.
Inferred read-onlyvibekit_db_tableBrowse rows of one table with pagination and optional sorting — a quick read-only alternative to hand-writing a SELECT.
Inferred read-onlyvibekit_list_deploysList an app's recent deploys, newest first, with status and commit info.
Inferred read-onlyvibekit_rollback_deployRoll an app back to a previous deploy (get the deployId from vibekit_list_deploys).
Inferred read-onlyvibekit_run_qaKick off an automated QA run (headless-browser checks) against a hosted app.
Inferred read-onlyvibekit_get_taskGet the status and result of a task submitted via vibekit_submit_task.
Inferred read-onlyvibekit_wait_for_taskBlock until a submitted task finishes (or the timeout), polling every 5 seconds, then return its result.
Inferred read-onlyvibekit_create_scheduleCreate a recurring coding task that the AI runs automatically on a cron schedule (e.
Potential side effectsvibekit_list_skillsList available implementation skills (IDs, names, descriptions, tags) from the VibeKit skills registry.
Inferred read-onlyvibekit_get_skillFetch the full content of a specific skill — implementation patterns, code examples, and best practices for a domain.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.vibekit]
url = "https://mcp.vibekit.bot/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"vibekit": {
"type": "http",
"url": "https://mcp.vibekit.bot/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: vibekit
Remote MCP URL: https://mcp.vibekit.bot/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"vibekit": {
"url": "https://mcp.vibekit.bot/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"vibekit": {
"type": "http",
"url": "https://mcp.vibekit.bot/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "vibekit",
"transport": "streamable-http",
"url": "https://mcp.vibekit.bot/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.