VibeKit

VibeKit Chat with Agent

vibekit_chat

Send a message to an app's built-in AI coding agent, which reads, writes, and modifies the app's code and redeploys it. Use for 'build/make a change to my app' requests. If the agent finishes quickly you get its reply directly. Otherwise you get status:'working' — do NOT resend; instead give the user LIVE progress: poll vibekit_agent_status every few seconds and relay the current step from activity.status ('editing the homepage…', 'deploying…') until activity.done, then read vibekit_agent_history for the final reply.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "appId": "<appId>",
      "message": "<message>"
    },
    "name": "vibekit_chat"
  }
}

Input Schema

Name	Required	Description	Default
`appId`	Yes	App ID (from vibekit_list_apps)
`message`	Yes	What you want the agent to do or change — be specific about features, design, and behavior.

Output Schema

Name	Required	Description
`ok`	Yes	Whether the call succeeded.
`data`	No	The agent's reply and remaining credit balance, or a status:'working' note with polling instructions when the coding turn is still running.
`error`	No	Error message when ok is false (e.g. missing/invalid VIBEKIT_API_KEY, or an API error).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 17, 2026

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": "The agent's reply and remaining credit balance, or a status:'working' note with polling instructions when the coding turn is still running."
+    },
+    "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"
+}

First observedJul 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations set openWorldHint=true and destructiveHint=false, but the description adds crucial async behavior: the agent may return a direct reply or a 'working' status, instructing not to resend but to poll. It also reveals the tool modifies code and redeploys, going well beyond the annotations.

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

Conciseness4/5

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

The description is moderately long but front-loaded with the core action. Every sentence serves a purpose: stating the action, usage scenario, and async handling. Could be slightly trimmed, but overall well-structured and efficient.

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?

For a complex async agent tool with two parameters and an output schema, the description covers the full lifecycle: sending, potential direct reply, polling via vibekit_agent_status, and final reply via vibekit_agent_history. It also mentions redeployment, making it comprehensively useful for an agent.

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 covers 100% of parameters, each with a description. The description adds context for appId (from vibekit_list_apps) and advises the user to be specific in message, which enhances the schema. Baseline 3 is appropriate given high schema coverage, but the added context justifies a 4.

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?

Description clearly states it sends a message to an AI coding agent to modify app code and redeploy. The verb 'send a message' and resource 'built-in AI coding agent' are specific, and the use case 'build/make a change' distinguishes it from sibling tools like vibekit_get_app or vibekit_deploy.

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?

Explicitly says when to use ('build/make a change to my app' requests) and provides detailed follow-up instructions: if status is 'working', poll vibekit_agent_status and then read vibekit_agent_history. Although it doesn't explicitly state when not to use, the guidance is very clear and actionable.

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

All VibeKit tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.