Skip to main content
Glama
Sign In
deenesjakoruzh
VibeKit MCP

VibeKit MCP

by VibeKit-Bot
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

vibekit-mcp

MCP-Server für VibeKit: Apps bereitstellen, Hosting verwalten und mit KI-Agenten von jedem MCP-Client aus chatten.

Dieses Paket ist für den VibeKit-Cloud-/API-Zugriff. Es verbindet nicht deine lokale Claude-Code-Instanz mit Telegram. Für die Fernsteuerung des lokalen Rechners verwende vibekit-agent.

Remote nutzen (ohne Installation)

VibeKit läuft auch als gehosteter Remote-Server, sodass Clients, die eine Remote-MCP-URL akzeptieren (claude.ai-Web-Connectors, ChatGPT usw.), keine Installation benötigen:

https://mcp.vibekit.bot/mcp?api_key=vk_your_api_key_here

Füge diese URL in das Feld „Custom Connector“ / „Remote-MCP-Server“ deines Clients ein. Clients, die das Setzen von Headern erlauben, können stattdessen Authorization: Bearer vk_your_api_key_here senden und die nackte URL https://mcp.vibekit.bot/mcp verwenden. Siehe API-Schlüssel abrufen unten.

Bevorzugst du eine lokale stdio-Installation (z. B. Claude Desktop)? Verwende die Schritte unten.

Related MCP server: vibekit-mcp

API-Schlüssel abrufen

Schlüssel beginnen mit vk_. Es gibt zwei Möglichkeiten, einen zu erhalten:

  • Sofort, ohne Anmeldung: Eine Anfrage liefert einen Schlüssel.

    curl -X POST https://vibekit.bot/api/v1/auth/register
# Response: {"apiKey": "vk_...", "plan": "free", "credits": 0}

    Speichere den zurückgegebenen Schlüssel und verwende ihn erneut. Jeder Aufruf von /auth/register erstellt ein brandneues Konto, also rufe ihn einmal auf, nicht pro Anfrage.

  • Über dein Konto: Wenn du VibeKit bereits nutzt, kopiere oder generiere deinen Schlüssel im Web-Dashboard oder in den Einstellungen der iOS-App.

Installation

npm install -g vibekit-mcp

Einrichtung

  1. Besorge dir einen VibeKit-API-Schlüssel (siehe API-Schlüssel abrufen oben).

  2. Füge ihn zur Konfiguration deines MCP-Clients hinzu (z. B. Claude Desktop) (~/Library/Application Support/Claude/claude_desktop_config.json unter macOS):

{
  "mcpServers": {
    "vibekit": {
      "command": "vibekit-mcp",
      "env": {
        "VIBEKIT_API_KEY": "vk_your_api_key_here"
      }
    }
  }
}

  1. Starte deinen MCP-Client neu

Verfügbare Tools

Hosting

Tool

Beschreibung

vibekit_list_apps

Alle gehosteten Apps auflisten

vibekit_get_app

Details zu einer bestimmten App abrufen

vibekit_list_templates

Startvorlagen für vibekit_create_app auflisten

vibekit_create_app

Neue App aus einer Vorlage erstellen

vibekit_deploy

GitHub-Repository auf Hosting bereitstellen

vibekit_redeploy

App mit dem neuesten Code erneut bereitstellen

vibekit_list_deploys

Die letzten Deployments einer App mit Status und Commit auflisten

vibekit_rollback_deploy

App auf ein früheres Deployment zurücksetzen

vibekit_app_logs

Anwendungsprotokolle abrufen

vibekit_restart_app

App neu starten

vibekit_stop_app

App stoppen

vibekit_start_app

Eine gestoppte App starten

vibekit_app_env

Umgebungsvariablen der App abrufen

vibekit_set_env

Umgebungsvariablen der App festlegen

vibekit_delete_app

App dauerhaft löschen

Agent

Tool

Beschreibung

vibekit_chat

Mit dem KI-Agenten einer App chatten

vibekit_agent_status

Agentenstatus abrufen

vibekit_agent_history

Chatverlauf mit dem Agenten abrufen

Datenbank

Tool

Beschreibung

vibekit_enable_database

Postgres-Datenbank für eine App aktivieren

vibekit_database_status

Datenbankstatus und Verbindungsinformationen abrufen

vibekit_db_schema

Das Datenbankschema abrufen (jede Tabelle und ihre Spalten)

vibekit_db_query

Eine schreibgeschützte SQL-Abfrage ausführen (nur SELECT, bis zu 200 Zeilen)

vibekit_db_table

Die Zeilen einer Tabelle mit Paginierung und Sortierung durchsuchen

QA

Tool

Beschreibung

vibekit_run_qa

Automatisierte QA-Tests ausführen

vibekit_qa_status

QA-Testergebnisse abrufen

Aufgaben

Tool

Beschreibung

vibekit_submit_task

Eine Programmieraufgabe einreichen

vibekit_get_task

Aufgabenstatus/-ergebnis abrufen

vibekit_list_tasks

Letzte Aufgaben auflisten

vibekit_wait_for_task

Auf Abschluss der Aufgabe warten

vibekit_cancel_task

Eine laufende Aufgabe abbrechen

vibekit_create_schedule

Wiederkehrende geplante Aufgabe erstellen

vibekit_list_schedules

Geplante Aufgaben auflisten

vibekit_delete_schedule

Geplante Aufgabe löschen

Konto

Tool

Beschreibung

vibekit_account

Kontoinformationen abrufen (Plan, Guthaben, Nutzung)

vibekit_list_skills

Implementierungs-Skills auflisten

vibekit_get_skill

Bestimmten Skill-Inhalt abrufen

Beispielverwendung

Nach der Konfiguration kannst du Aufforderungen wie die folgenden verwenden:

  • „Mein GitHub-Repository auf VibeKit bereitstellen und eine neue App erstellen“

  • „Mit dem KI-Agenten meiner App über das Hinzufügen eines Kontaktformulars chatten“

  • „Zeig mir die Protokolle meiner App und starte sie neu, wenn Fehler auftreten“

  • „Eine Datenbank für meine App aktivieren, dann ihr Schema anzeigen und die Benutzertabelle abfragen“

  • „Die letzten Deployments meiner App auflisten und auf das letzte funktionierende zurücksetzen“

  • „QA-Tests auf meiner bereitgestellten App ausführen“

  • „Mein VibeKit-Kontoguthaben prüfen und meine Apps auflisten“

  • „Einen wöchentlichen Zeitplan erstellen, um die Leistung meiner App zu verbessern“

Umgebungsvariablen

Variable

Beschreibung

Standard

VIBEKIT_API_KEY

Dein VibeKit-API-Schlüssel (erforderlich)

keine

VIBEKIT_API_URL

API-Basis-URL

https://vibekit.bot/api/v1

Verwandte Pakete

  • vibekit-cli: Terminal-Client für VibeKit-Cloud-Workflows

  • vibekit-agent: Telegram-Brücke für lokales Claude Code auf deinem eigenen Rechner

Links

Datenschutzerklärung

Die Datenschutzerklärung von VibeKit: https://vibekit.bot/privacy

Was dieser MCP-Server konkret mit deinen Daten macht:

  • Jeder Tool-Aufruf wird an die VibeKit-API (https://vibekit.bot/api/v1) über HTTPS weitergeleitet, authentifiziert mit dem von dir konfigurierten API-Schlüssel. Tool-Eingaben und -Ausgaben werden von VibeKit verarbeitet, um deine Apps und Agenten auszuführen, gemäß der obigen Datenschutzerklärung.

  • Der Server selbst speichert keinen Zustand: Es wird nichts auf die Festplatte geschrieben, keine Analysen oder Telemetrie werden von diesem Paket erfasst, und dein API-Schlüssel wird aus der Konfiguration gelesen (VIBEKIT_API_KEY / das Schlüsselfeld der Erweiterung) und nur an vibekit.bot gesendet.

  • Datenaufbewahrung, Weitergabe an Dritte und Löschung unterliegen der obigen Richtlinie. Fragen: support@vibekit.bot.

Available Tools

2 tools
vibekit_database_statusVibeKit Database StatusA
Read-onlyIdempotent
Inspect

Get an app's database status and connection info (whether it's provisioned, frozen, etc.).

NameRequiredDescriptionDefault
appIdYesApp ID (from vibekit_list_apps)

Output Schema

NameRequiredDescription
okYesWhether the call succeeded.
dataNoDatabase stats: tables, storage, and connection info.
errorNoError message when ok is false (e.g. missing/invalid VIBEKIT_API_KEY, or an API error).

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and idempotentHint. The description adds minimal behavioral context (e.g., 'whether it's provisioned, frozen, etc.') but does not reveal additional traits. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. Every element is purposeful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, the description need not explain return values. It covers the essential purpose and mentions example states. Could be slightly more specific but is adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a description for 'appId'. The tool description adds no extra meaning beyond the schema, so baseline score applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get an app's database status and connection info', which uses the verb 'Get' and specifies the resource. It distinguishes from siblings like 'vibekit_db_query' and 'vibekit_enable_database' by focusing solely on status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. The description only states what it does, leaving the agent to infer context from sibling tool names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

vibekit_get_taskVibeKit Get TaskA
Read-only
Inspect

Get the status and result of a task submitted via vibekit_submit_task.

NameRequiredDescriptionDefault
taskIdYesTask ID returned from vibekit_submit_task

Output Schema

NameRequiredDescription
okYesWhether the call succeeded.
dataNoTask details: status, logs/result summary, and repo info.
errorNoError message when ok is false (e.g. missing/invalid VIBEKIT_API_KEY, or an API error).

TDQS

A4.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already set readOnlyHint=true, indicating no side effects. The description adds no further behavioral details (e.g., re-fetch behavior, error states). With annotations covering safety, the description meets the baseline but does not exceed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence that directly conveys the purpose without fluff. Every word is necessary; no redundancy or extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description doesn't need to detail return values. The one-parameter tool is fully covered by the description and schema, leaving no gaps for an agent to misinterpret.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with description for taskId. The description adds value by specifying that the ID comes from vibekit_submit_task, linking the tools together and clarifying the parameter's origin.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'status and result of a task', and distinguishes it from sibling tools like vibekit_submit_task (creates) and vibekit_cancel_task (cancels). It references the specific submission tool, making purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use after vibekit_submit_task. It does not explicitly mention when not to use or alternatives like vibekit_wait_for_task for polling, but the context is clear enough for an agent to infer appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 31 tool updatesv0.7.5
    • Removedvibekit_account
    • Removedvibekit_agent_history
    • Removedvibekit_agent_status
    • Removedvibekit_app_env
    • Removedvibekit_app_logs
    • Removedvibekit_cancel_task
    • Removedvibekit_chat
    • Removedvibekit_create_app
    • Removedvibekit_create_schedule
    • Changedvibekit_database_status2 fields changed
      • changedInput schema / properties / appId / description
        Previous value: -"The app ID to get database status for"New value: +"App ID (from vibekit_list_apps)"
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "description": "Result envelope: ok=true with data on success, ok=false with error on failure.",
+  "properties": {
+    "data": {
+      "description": "Database stats: tables, storage, and connection info."
+    },
+    "error": {
+      "description": "Error message when ok is false (e.g. missing/invalid VIBEKIT_API_KEY, or an API error).",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the call succeeded.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}
    • Removedvibekit_delete_app
    • Removedvibekit_delete_schedule
    • Removedvibekit_deploy
    • Removedvibekit_enable_database
    • Removedvibekit_get_app
    • Removedvibekit_get_skill
    • Changedvibekit_get_task2 fields changed
      • changedInput schema / properties / taskId / description
        Previous value: -"The task ID returned from vibekit_submit_task"New value: +"Task ID returned from vibekit_submit_task"
      • changedOutput schema / (root)
        Previous value: -nullNew value: +{
+  "description": "Result envelope: ok=true with data on success, ok=false with error on failure.",
+  "properties": {
+    "data": {
+      "description": "Task details: status, logs/result summary, and repo info."
+    },
+    "error": {
+      "description": "Error message when ok is false (e.g. missing/invalid VIBEKIT_API_KEY, or an API error).",
+      "type": "string"
+    },
+    "ok": {
+      "description": "Whether the call succeeded.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "ok"
+  ],
+  "type": "object"
+}
    • Removedvibekit_list_apps
    • Removedvibekit_list_schedules
    • Removedvibekit_list_skills
    • Removedvibekit_list_tasks
    • Removedvibekit_list_templates
    • Removedvibekit_qa_status
    • Removedvibekit_redeploy
    • Removedvibekit_restart_app
    • Removedvibekit_run_qa
    • Removedvibekit_set_env
    • Removedvibekit_start_app
    • Removedvibekit_stop_app
    • Removedvibekit_submit_task
    • Removedvibekit_wait_for_task
  2. 31 tool updatesv0.6.1
    • First observedvibekit_account
    • First observedvibekit_agent_history
    • First observedvibekit_agent_status
    • First observedvibekit_app_env
    • First observedvibekit_app_logs
    • First observedvibekit_cancel_task
    • First observedvibekit_chat
    • First observedvibekit_create_app
    • First observedvibekit_create_schedule
    • First observedvibekit_database_status
    • First observedvibekit_delete_app
    • First observedvibekit_delete_schedule
    • First observedvibekit_deploy
    • First observedvibekit_enable_database
    • First observedvibekit_get_app
    • First observedvibekit_get_skill
    • First observedvibekit_get_task
    • First observedvibekit_list_apps
    • First observedvibekit_list_schedules
    • First observedvibekit_list_skills
    • First observedvibekit_list_tasks
    • First observedvibekit_list_templates
    • First observedvibekit_qa_status
    • First observedvibekit_redeploy
    • First observedvibekit_restart_app
    • First observedvibekit_run_qa
    • First observedvibekit_set_env
    • First observedvibekit_start_app
    • First observedvibekit_stop_app
    • First observedvibekit_submit_task
    • First observedvibekit_wait_for_task
Deploy Server
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

TDQS

A3.9/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one checks database status, the other retrieves task results. No ambiguity.

Naming Consistency5/5

Both tools use the consistent 'vibekit_' prefix followed by verb_noun pattern (database_status, get_task), showing good naming uniformity.

Tool Count2/5

Only 2 tools for a server named 'VibeKit MCP' is too few, especially since a referenced tool (vibekit_submit_task) is missing, making the set feel incomplete.

Completeness2/5

The tool set is missing a critical tool (vibekit_submit_task) that is referenced in vibekit_get_task, and there are obvious gaps in domain coverage beyond database status and task retrieval.

Maintenance

ActivityMaintained
ResponsivenessUnresponsive

Resources

Related MCP Connectors

Related MCP Servers

  • vibekit-mcp

    vibekit-apps
    A
    license
    B
    quality
    D
    maintenance
    Enables the management of AI-powered VibeKit apps, allowing users to control deployments, monitor logs, and perform database operations directly from MCP-compatible clients. It facilitates interaction with hosted AI agents and the execution of headless coding tasks through natural language.
    49
    10 npm
    MIT

  • dothub

    catancs
    F
    license
    Not graded
    quality
    D
    maintenance
    Publish your Claude Code setup, browse a public feed, and pull setups in. Remote MCP server + web feed in one FastAPI app.
    1
    -