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/ColtonWilley/ue-llm-toolkitWrote 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/coltonwilley/ue-llm-toolkit/uellmtoolkit-ue-llm-toolkit)<a href="https://agentmods.dev/mcp/coltonwilley/ue-llm-toolkit/uellmtoolkit-ue-llm-toolkit"><img src="https://agentmods.dev/badge/mcp/coltonwilley/ue-llm-toolkit/uellmtoolkit-ue-llm-toolkit/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/coltonwilley/ue-llm-toolkit/uellmtoolkit-ue-llm-toolkit"><img src="https://agentmods.dev/badge/mcp/coltonwilley/ue-llm-toolkit/uellmtoolkit-ue-llm-toolkit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ue-llm-toolkit 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 13d 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
{
"ue-llm-toolkit": {
"command": "node",
"args": [
"Resources/mcp-bridge/index.js"
],
"env": {
"UNREAL_MCP_URL": "http://localhost:3000"
}
}
}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.
- 13d ago First seen · 11 lines scan A 361d1d7b74aa
ue-llm-toolkit is an MCP server published in the GitHub repository ColtonWilley/ue-llm-toolkit (102 stars, last pushed 5mo 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 2026-08-30.
Other mcp servers, from other repositories
summer-engine
Local Summer CLI and MCP server for Summer Engine. Install and run the engine, connect Claude Code, Cursor, Codex, Gemini, and other agents, and build real games with bundled skills, hooks, and plugins. Runs locally from the summer-engine npm package.
godot-mcp
MCP server for full Godot 4.x engine control with 165 tools for AI-driven game development. Runs locally from the @tugcantopaloglu/godot-mcp npm package.
chess
MCP server "chess" as configured in alegerber/stockfish-lc0-mcp. Runs dist/index.js with node. Needs 3 environment variables to run.
mc-pack-builder-mcp
MCP server "mc-pack-builder-mcp" as configured in dcd887/mc-pack-builder-mcp. Runs locally from the mc-pack-builder-mcp npm package.
rankedtoday-mcp
League of Legends MCP server — MMR estimation from LP flow, climb projections, KDA, hours played, and cognitive-readiness reference. No API key. Runs locally from the rankedtoday-mcp Python package.
blender-mcp-2-79
MCP server "blender-mcp-2-79" as configured in AaronBrunckhurst/blender-mcp-2.79. Runs locally from the blender-mcp-2-79 Python package.