Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add finasteos/gamedev-mcp-hub --skill mcp-buildergit clone --depth 1 https://github.com/finasteos/gamedev-mcp-hubWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/finasteos/gamedev-mcp-hub/mcp-builder)<a href="https://agentmods.dev/skills/finasteos/gamedev-mcp-hub/mcp-builder"><img src="https://agentmods.dev/badge/skills/finasteos/gamedev-mcp-hub/mcp-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/finasteos/gamedev-mcp-hub/mcp-builder"><img src="https://agentmods.dev/badge/skills/finasteos/gamedev-mcp-hub/mcp-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00047 | $0.03157 |
| Opus 5 | $0.00023 | $0.01579 |
| Sonnet 5 | $0.00009 | $0.00631 |
| Haiku 4.5 | $0.00005 | $0.00316 |
Grade A, and why
mcp-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 530 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Builder Skill - GameDev MCP Hub
Build production-quality MCP servers to integrate game development tools and services into the GameDev MCP Hub.
OVERVIEW
This skill guides you through creating MCP servers that integrate external game development services into the hub. An MCP server provides tools that allow AI to interact with game engines, 3D software, asset libraries, version control, and other gamedev services.
Quality is measured by: How well the server enables AI to accomplish real game development tasks.
GAMEDEV MCP HUB CONTEXT
What is the Hub?
The GameDev MCP Hub is a centralized gateway that:
- Aggregates multiple MCP servers (Blender, Obsidian, GitHub, Godot, etc.)
- Provides a unified interface for AI clients
- Manages server lifecycle and connections
- Routes tool calls to appropriate servers
Current Hub Architecture
Existing servers:
- Obsidian (18 tools) - Knowledge management
- Blender (17 tools) - 3D modeling and rendering
- GitHub (43 tools) - Version control
- Godot (~22 tools) - Game engine operations
- Thingiverse (~10 tools) - 3D model library
Your new server will:
- Join this ecosystem
- Be configured in
config/mcp-servers.json - Run as a separate process managed by the hub
- Expose tools through the MCP protocol
PHASE 1: RESEARCH & PLANNING
1.1 Understand Agent-Centric Design
Build for Workflows, Not Just API Endpoints:
- Don't wrap APIs 1:1 - create workflow tools
- Consolidate operations (e.g.,
create_scene_with_characternot justcreate_scene) - Focus on complete tasks AI actually needs
Optimize for Limited Context:
- Return high-signal information only
- Provide "concise" vs "detailed" modes
- Use names over IDs (e.g., "PlayerCharacter" not "uuid-1234")
Actionable Error Messages:
- Guide AI toward correct usage
- Suggest specific next steps
- Make errors educational
1.2 Study MCP Protocol
Fetch latest documentation:
WebFetch: https://modelcontextprotocol.io/llms-full.txt
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 530 lines · 47 tokens per session scan A 312d07e37e49
mcp-builder is a skill published in the GitHub repository finasteos/gamedev-mcp-hub (0 stars, last pushed 1mo ago), licensed MIT. It adds 47 tokens to every session and 3,157 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gameobject-component-destroy
Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.
unity-version-split
Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).
godot-signals-groups
Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
motion
How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.
threejs-exposure-color-grading
Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.