Playgama MCP - Publish & Manage HTML5 Games

Create a game

create_application

Destructive

Create a draft game. Answers its id, which the other tools take. Titles are not unique: if a call failed without a clear answer, check list_applications before creating again.

Input Schema

TableJSON Schema

Name	Required	Description
`agent`	No	The coding agent the game was made with: claude-code (Claude Code), codex (Codex), cursor (Cursor), antigravity (Google Antigravity), opencode (OpenCode), gemini-cli (Gemini CLI), kimi-code (Kimi Code Agent), grok-build (Grok Build), workbuddy (WorkBuddy), zcode (ZCode), claude-app (Claude app (chat / Desktop)), chatgpt (ChatGPT (chat)), other (Other), none (No AI agent)
`model`	No	The model behind that agent: claude-fable (Claude Fable), claude-opus (Claude Opus), claude-sonnet (Claude Sonnet), claude-haiku (Claude Haiku), openai-astra (OpenAI Astra), openai-sol (OpenAI Sol), openai-luna (OpenAI Luna), openai-terra (OpenAI Terra), gemini-pro (Gemini Pro), gemini-flash (Gemini Flash), grok (Grok), kimi (Kimi), qwen (Qwen), deepseek (DeepSeek), glm (GLM), other (Other)
`title`	Yes	The game’s title in English — Latin letters, digits, spaces and punctuation, up to 120 characters. Shown to players and moderators as-is.
`engine`	Yes	The engine the game was built with: unity (Unity), construct3 (Construct 3), cocos-creator (Cocos Creator), defold (Defold), godot (Godot), gdevelop (GDevelop), game_maker (Game Maker), scratch (Scratch), js (plain JavaScript, no engine)
`modelId`	No	The exact model behind that agent, as your runtime names it, e.g. claude-opus-5-5 or anthropic/claude-opus-5.5. Stored lowercased, without the vendor prefix or a :variant suffix. When the id names a known family, that family is stored as model, over the one sent.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 15, 2026

changedInput schema / properties / modelId / description

Previous value: -"The exact model behind that agent, as your runtime names it, e.g. claude-opus-5-5 or anthropic/claude-opus-5.5. Stored lowercased, without the vendor prefix or a :variant suffix. A game with no model yet gets the family of this id when the id names a known one."New value: +"The exact model behind that agent, as your runtime names it, e.g. claude-opus-5-5 or anthropic/claude-opus-5.5. Stored lowercased, without the vendor prefix or a :variant suffix. When the id names a known family, that family is stored as model, over the one sent."

Changed1 schema field changedOct 12, 2026

addedInput schema / properties / modelId

Added value: +{
+  "description": "The exact model behind that agent, as your runtime names it, e.g. claude-opus-5-5 or anthropic/claude-opus-5.5. Stored lowercased, without the vendor prefix or a :variant suffix. A game with no model yet gets the family of this id when the id names a known one.",
+  "maxLength": 100,
+  "type": "string"
+}

Changed4 schema fields changedSep 28, 2026

changedInput schema / properties / agent / description

Previous value: -"The coding agent the game was made with: claude-code (Claude Code), codex (Codex), cursor (Cursor), kimi-code (Kimi Code Agent), grok-build (Grok Build), workbuddy (WorkBuddy), other (Other), none (No AI agent)"New value: +"The coding agent the game was made with: claude-code (Claude Code), codex (Codex), cursor (Cursor), antigravity (Google Antigravity), opencode (OpenCode), gemini-cli (Gemini CLI), kimi-code (Kimi Code Agent), grok-build (Grok Build), workbuddy (WorkBuddy), zcode (ZCode), claude-app (Claude app (chat / Desktop)), chatgpt (ChatGPT (chat)), other (Other), none (No AI agent)"

changedInput schema / properties / agent / enum

Previous value: -[
-  "claude-code",
-  "codex",
-  "cursor",
-  "kimi-code",
-  "grok-build",
-  "workbuddy",
-  "other",
-  "none"
-]New value: +[
+  "claude-code",
+  "codex",
+  "cursor",
+  "antigravity",
+  "opencode",
+  "gemini-cli",
+  "kimi-code",
+  "grok-build",
+  "workbuddy",
+  "zcode",
+  "claude-app",
+  "chatgpt",
+  "other",
+  "none"
+]

changedInput schema / properties / model / description

Previous value: -"The model behind that agent: claude-fable (Claude Fable), claude-opus (Claude Opus), claude-sonnet (Claude Sonnet), claude-haiku (Claude Haiku), openai-astra (OpenAI Astra), openai-sol (OpenAI Sol), openai-luna (OpenAI Luna), openai-terra (OpenAI Terra), grok (Grok), kimi (Kimi), other (Other)"New value: +"The model behind that agent: claude-fable (Claude Fable), claude-opus (Claude Opus), claude-sonnet (Claude Sonnet), claude-haiku (Claude Haiku), openai-astra (OpenAI Astra), openai-sol (OpenAI Sol), openai-luna (OpenAI Luna), openai-terra (OpenAI Terra), gemini-pro (Gemini Pro), gemini-flash (Gemini Flash), grok (Grok), kimi (Kimi), qwen (Qwen), deepseek (DeepSeek), glm (GLM), other (Other)"

changedInput schema / properties / model / enum

Previous value: -[
-  "claude-fable",
-  "claude-opus",
-  "claude-sonnet",
-  "claude-haiku",
-  "openai-astra",
-  "openai-sol",
-  "openai-luna",
-  "openai-terra",
-  "grok",
-  "kimi",
-  "other"
-]New value: +[
+  "claude-fable",
+  "claude-opus",
+  "claude-sonnet",
+  "claude-haiku",
+  "openai-astra",
+  "openai-sol",
+  "openai-luna",
+  "openai-terra",
+  "gemini-pro",
+  "gemini-flash",
+  "grok",
+  "kimi",
+  "qwen",
+  "deepseek",
+  "glm",
+  "other"
+]

Changed4 schema fields changedSep 23, 2026

changedInput schema / properties / agent / description

Previous value: -"The coding agent the game was made with: claude-code (Claude Code), codex (Codex), cursor (Cursor), other (another agent), none (no agent, written by hand)"New value: +"The coding agent the game was made with: claude-code (Claude Code), codex (Codex), cursor (Cursor), kimi-code (Kimi Code Agent), grok-build (Grok Build), workbuddy (WorkBuddy), other (Other), none (No AI agent)"

changedInput schema / properties / agent / enum

Previous value: -[
-  "claude-code",
-  "codex",
-  "cursor",
-  "other",
-  "none"
-]New value: +[
+  "claude-code",
+  "codex",
+  "cursor",
+  "kimi-code",
+  "grok-build",
+  "workbuddy",
+  "other",
+  "none"
+]

changedInput schema / properties / model / description

Previous value: -"The model family behind that agent: claude (Claude), gpt (GPT), gemini (Gemini), other (another model)"New value: +"The model behind that agent: claude-fable (Claude Fable), claude-opus (Claude Opus), claude-sonnet (Claude Sonnet), claude-haiku (Claude Haiku), openai-astra (OpenAI Astra), openai-sol (OpenAI Sol), openai-luna (OpenAI Luna), openai-terra (OpenAI Terra), grok (Grok), kimi (Kimi), other (Other)"

changedInput schema / properties / model / enum

Previous value: -[
-  "claude",
-  "gpt",
-  "gemini",
-  "other"
-]New value: +[
+  "claude-fable",
+  "claude-opus",
+  "claude-sonnet",
+  "claude-haiku",
+  "openai-astra",
+  "openai-sol",
+  "openai-luna",
+  "openai-terra",
+  "grok",
+  "kimi",
+  "other"
+]

Changed2 schema fields changedSep 22, 2026

addedInput schema / properties / agent

Added value: +{
+  "description": "The coding agent the game was made with: claude-code (Claude Code), codex (Codex), cursor (Cursor), other (another agent), none (no agent, written by hand)",
+  "enum": [
+    "claude-code",
+    "codex",
+    "cursor",
+    "other",
+    "none"
+  ],
+  "type": "string"
+}

addedInput schema / properties / model

Added value: +{
+  "description": "The model family behind that agent: claude (Claude), gpt (GPT), gemini (Gemini), other (another model)",
+  "enum": [
+    "claude",
+    "gpt",
+    "gemini",
+    "other"
+  ],
+  "type": "string"
+}

First observedSep 11, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already carry readOnly=false, destructiveHint=true and idempotentHint=false; the description adds real context on top by explaining the non-idempotency rationale (non-unique titles mean duplicate retries create duplicates) and by disclosing the created object's state ('draft') and its returned id. It doesn't explain what makes the operation destructive (quota, irreversibility), which would be the remaining useful detail.

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?

Two short sentences with zero filler. The core action and return value come first, and the retry caveat follows, so it is properly front-loaded.

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?

Five parameters at full schema coverage, no nested objects, and no output schema — and the description supplies the one thing the missing output schema would have carried, namely that the response yields the id used by sibling tools. Nothing needed to call this correctly is absent.

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 description coverage is 100% with three enum-backed parameters fully documented, so the schema does the heavy lifting and a baseline 3 applies. The description only indirectly touches the `title` parameter (non-unique), adding no syntax or format detail beyond the schema.

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?

States a specific verb and resource ('Create a draft game') and adds the crucial scope qualifier 'draft', which distinguishes it from publish/launch siblings. It also names the returned artifact ('Answers its `id`, which the other tools take'), telling the agent exactly how the result feeds downstream calls.

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?

Gives an explicit routing rule: titles are not unique, so after an ambiguous failure check list_applications before retrying. That is a genuine when-to-use-alternative instruction. It doesn't cover prerequisites (e.g. account/submission state) or when the tool should simply not be called, so it falls short of a 5.

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

All Playgama MCP - Publish & Manage HTML5 Games tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?