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.
git clone --depth 1 https://github.com/moonolgerd/game-mcpInstalling this writes the configuration, not the program: `GameMcpServer` has to be on your PATH already, or the server will not start.
Wrote 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/mcp/moonolgerd/game-mcp/mcp-game-mcp)<a href="https://agentmods.dev/mcp/moonolgerd/game-mcp/mcp-game-mcp"><img src="https://agentmods.dev/badge/mcp/moonolgerd/game-mcp/mcp-game-mcp/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/mcp/moonolgerd/game-mcp/mcp-game-mcp"><img src="https://agentmods.dev/badge/mcp/moonolgerd/game-mcp/mcp-game-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
game-mcp 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 1mo 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.
What it actually says
{
"game-mcp": {
"command": "GameMcpServer",
"args": [],
"env": {}
}
}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.
- 1mo ago First seen · 7 lines scan A 9407e26ec737
game-mcp is an MCP server published in the GitHub repository moonolgerd/game-mcp (0 stars, last pushed 8mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 mcp servers, from other repositories
unreal-engine-mcp
EngineWire: drive the Unreal Editor (UE 5.0-5.8): levels, Blueprints, UI, materials, VFX and more. Runs locally from the unreal-engine-mcp-server npm package. Needs 11 environment variables to run.
ChiR24-unreal_mcp
Control Unreal Engine to browse assets, import content, and manage levels and sequences. Automate… Remote server at server.smithery.ai.
ChiR24-unreal_mcp_server
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal E… Remote server at server.smithery.ai.
godot-mcp-runtime
Zero-addon MCP server for Godot 4: agents edit, run, and play-test the game. Runs locally from the godot-mcp-runtime npm package. Needs 5 environment variables to run.
playcanvas
The PlayCanvas Editor MCP Server. Runs locally from the @playcanvas/editor-mcp-server npm package.
rbx-studio
MCP server "rbx-studio" as configured in EL4CTEO/rbx-studio-mcp. Runs ./dist/index.js with node.