Google PageRank for AI agents. 25,000+ tools indexed.

monolith MCP Server

tumourlove/monolith

Score: 78.8 ↓ 0.9% Rank #2257 MCP Server
[![AgentRank](https://agentrank-ai.com/api/v1/badge/tumourlove--monolith)](https://agentrank-ai.com/tool/tumourlove--monolith/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of tumourlove/monolith? Claim this listing →

MCP plugin for Unreal Engine 5.7 & 5.8 — gives AI assistants full read/write access to Blueprints, Materials, Niagara, Animation, Mesh, AI, GAS, Logic Driver, ComboGraph, UI, Audio, plus Reflection Intelligence (decision / risk / C++ reflection / replication queries). 1,400+ actions across 25+ namespaces. Native C++, zero Python dependency.

Add AgentRank to Claude Code Discover and compare tools like tumourlove/monolith — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

tumourlove/monolith is a C++ tool licensed under MIT. MCP plugin for Unreal Engine 5.7 & 5.8 — gives AI assistants full read/write access to Blueprints, Materials, Niagara, Animation, Mesh, AI, GAS, Logic Driver, ComboGraph, UI, Audio, plus Reflection Intelligence (decision / risk / C++ reflection / replication queries). 1,400+ actions across 25+ namespaces. Native C++, zero Python dependency. Topics: ai, ai-tools, animation, blueprint, claude, claude-code, cursor, material-editor, mcp, model-context-protocol, niagara, ue5-plugin, unreal-engine, unreal-engine-5, unreal-engine-plugin, vfx, gameplay-ability-system, mesh, procedural-generation, audio.

Ranked #2257 out of 24846 indexed tools.

In the top 10% of all indexed tools.

Has 14 contributors.

Ecosystem

C++ MIT
aiai-toolsanimationblueprintclaudeclaude-codecursormaterial-editormcpmodel-context-protocolniagaraue5-pluginunreal-engineunreal-engine-5unreal-engine-pluginvfxgameplay-ability-systemmeshprocedural-generationaudio

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 330

330 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 76%

56/74 issues closed → decent issue management

Contributors 10% 14

14 contributors → active community

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 87
Description Detailed
License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Freshness high impact

Last commit was 49 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for tumourlove/monolith
[![AgentRank](https://agentrank-ai.com/api/v1/badge/tumourlove--monolith)](https://agentrank-ai.com/tool/tumourlove--monolith/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/tumourlove--monolith/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/tumourlove--monolith" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="tumourlove/monolith"></script>

Matched Queries

"mcp plugin"topic:mcptopic:model-context-protocol

From the README

# Monolith

**One plugin. Every Unreal domain. Zero dependencies.**

---

## Why I built this

Most MCP integrations for Unreal register every action as a separate tool. That floods the AI's context window with hundreds of tool names before you've asked a single question — and the actually useful stuff gets buried. I built Monolith because I wanted my AI to spend its context on my problem, not on memorising a tool catalogue.

One plugin. One MCP endpoint. A handful of namespace-dispatch tools instead of ~1,400+. The AI calls `monolith_discover()` and `monolith_guide()` when it needs to know what's available, and otherwise just hits `blueprint_query("create_blueprint", ...)`, `material_query("compile", ...)`, and so on. `monolith_discover()` is terse by default — each action returns just a name and a one-line description, so listing a namespace costs almost nothing; the full param schema is one `describe_query("action_schema", ...)` call (or `detail=true`) away when the AI actually need
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.