Vibekit

49 tools. 27 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated:

27 can modify or destroy data
22 read-only
49 tools total

Community server · catalogue entry verified 03/07/2026

How to control Vibekit ↓

What Vibekit exposes to your agents

Read (22) Write / Execute (21) Destructive / Financial (6)
Critical Risk

The most dangerous Vibekit tools

27 of Vibekit's 49 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Vibekit

PolicyLayer is an MCP gateway — it sits between your AI agents and Vibekit, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations
{
  "vibekit_agent_reset": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "vibekit_add_domain": {
    "limits": [
      {
        "counter": "vibekit_add_domain_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "vibekit_account": {
    "limits": [
      {
        "counter": "vibekit_account_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

  1. Create a free account and register Vibekit — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON VIBEKIT →

Instant setup, no code required.

All 49 Vibekit tools

READ 22 tools
Read vibekit_account Get VibeKit account info — plan, credits balance, session usage, and limits. Read vibekit_agent_config Get the AI agent configuration for an app. Returns the current model. Read vibekit_agent_history Get the chat history with an app Read vibekit_agent_status Get the current status of an app Read vibekit_app_env Get environment variables for a hosted app. Read vibekit_app_logs Get application logs for debugging and monitoring. Read vibekit_app_schedules List cron schedules configured for an app Read vibekit_database_schema Get the database schema (tables and columns) for an app Read vibekit_database_status Get database status and connection info for an app. Read vibekit_deploy_history List deployment history for an app so you can roll back to a previous snapshot. Read vibekit_file_changes Get a diff of recent file changes in an app Read vibekit_get_app Get details about a specific hosted app including status, URL, plan, and usage. Read vibekit_get_skill Fetch the full content of a specific skill. Use vibekit_list_skills to discover available skill IDs. Read vibekit_get_task Get the status and result of a previously submitted task. Read vibekit_list_apps List all hosted apps in your VibeKit account. Read vibekit_list_files List files in an app Read vibekit_list_schedules List all account-level recurring task schedules. Read vibekit_list_skills List available implementation skills. Skills contain code patterns and best practices for specific domains. Read vibekit_list_tasks List recent tasks submitted to VibeKit. Read vibekit_qa_status Get the latest QA test results for an app. Read vibekit_read_file Read the contents of a file in an app Read vibekit_rollback Roll back an app to a previous deployment snapshot.

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

Questions about Vibekit

Can an AI agent delete data through the Vibekit MCP server? +

Yes. The Vibekit server exposes 6 destructive tools including vibekit_agent_reset, vibekit_delete_app, vibekit_delete_app_schedule. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Vibekit? +

The Vibekit server has 8 write tools including vibekit_add_domain, vibekit_agent_set_model, vibekit_create_app. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Vibekit.

How many tools does the Vibekit MCP server expose? +

49 tools across 4 categories: Destructive, Execute, Read, Write. 22 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on Vibekit? +

Register the Vibekit MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Vibekit tool call.

Deterministic rules across all 49 Vibekit tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

49 Vibekit tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.