Borrowing it
Nothing to install: this file belongs to remiphilippe/mcp-unreal. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/remiphilippe/mcp-unreal/main/CLAUDE.mdgit clone --depth 1 https://github.com/remiphilippe/mcp-unrealWrote 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/instructions/remiphilippe/mcp-unreal/claude-md)<a href="https://agentmods.dev/instructions/remiphilippe/mcp-unreal/claude-md"><img src="https://agentmods.dev/badge/instructions/remiphilippe/mcp-unreal/claude-md/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/instructions/remiphilippe/mcp-unreal/claude-md"><img src="https://agentmods.dev/badge/instructions/remiphilippe/mcp-unreal/claude-md.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 | $0.06281 | $0.06281 |
| Opus 5.5 | $0.02512 | $0.02512 |
| Sonnet 5.5 | $0.01256 | $0.01256 |
| Haiku 4.5 | $0.00628 | $0.00628 |
Grade A, and why
mcp-unreal CLAUDE.md 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 2mo 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 — 590 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — mcp-unreal
Model Context Protocol server for Unreal Engine 5.7. Single Go binary. Repository: https://github.com/remiphilippe/mcp-unreal License: Apache-2.0
Project Overview
This is an MCP (Model Context Protocol) server written in Go that gives AI coding agents (Claude Code, Cursor, etc.) complete autonomous control over an Unreal Engine 5.7 project — builds, tests, editor manipulation, Blueprint editing, procedural mesh generation, and documentation lookup.
Read IMPLEMENTATION.md before writing any code. It contains the full architecture, tool inventory, communication paths, and design decisions.
Key Facts
- Language: Go (primary), C++ (UE editor plugin only)
- MCP SDK:
github.com/modelcontextprotocol/go-sdk/mcp(official, co-maintained with Google) - Transport: stdio (JSON-RPC 2.0) — Claude Code launches the binary as a subprocess
- Doc search:
github.com/blevesearch/bleve/v2(compiled into the binary, no external service) - Target UE version: 5.7 (macOS primary, Windows and Linux secondary)
- Go version: 1.25+
Repository Structure
mcp-unreal/
├── cmd/
│ └── mcp-unreal/
│ └── main.go # Entry point, CLI flags, tool registration
├── internal/
│ ├── config/
│ │ └── config.go # Environment config, project detection, path resolution
│ ├── headless/
│ │ ├── build.go # build_project, cook_project, generate_project_files
│ │ ├── build_test.go
│ │ ├── test.go # run_tests, run_visual_tests, list_tests
│ │ ├── test_test.go
│ │ └── log.go # get_test_log
│ ├── editor/
│ │ ├── client.go # HTTP client for RC API + plugin
│ │ ├── client_test.go
│ │ ├── actors.go # Actor CRUD tools
│ │ ├── actors_test.go
│ │ ├── properties.go # set_property, get_property, call_function
│ │ ├── blueprints.go # blueprint_query, blueprint_modify
│ │ ├── anim_blueprints.go # anim_blueprint_query, anim_blueprint_modify
│ │ ├── assets.go # search_assets, get_asset_info
│ │ ├── materials.go # material_ops
│ │ ├── characters.go # character_config
│ │ ├── input.go # input_ops
│ │ ├── mesh.go # procedural_mesh, realtime_mesh
│ │ ├── levels.go # level_ops
│ │ └── utilities.go # console cmd, output log, viewport, scripts
│ ├── docs/
│ │ ├── index.go # Bleve index open/create/query
│ │ ├── index_test.go
│ │ ├── lookup.go # lookup_docs, lookup_class tool handlers
│ │ ├── ingest.go # Markdown → bleve doc entries
│ │ └── class_parser.go # Parse UE class reference markdown
│ └── status/
│ └── status.go # status tool, connectivity checks
├── docs/ # Documentation source files for the index
│ ├── ue5.7/
│ ├── realtimemesh/
│ └── README.md # How to add/update doc entries
├── plugin/ # UE 5.7 C++ editor plugin
│ ├── MCPUnreal.uplugin
│ ├── Source/
│ │ └── MCPUnreal/
│ │ ├── MCPUnreal.Build.cs
│ │ └── ...
│ └── README.md # Plugin build/install instructions
├── .github/
│ ├── workflows/
│ │ ├── ci.yml # Go lint + test + build
│ │ └── release.yml # GoReleaser on tag push
│ └── ISSUE_TEMPLATE/
│ ├── bug_report.md
│ └── feature_request.md
├── IMPLEMENTATION.md # Full architecture document
├── CLAUDE.md # This file
├── CONTRIBUTING.md
├── LICENSE # Apache-2.0
├── README.md # User-facing: install, configure, use
├── SECURITY.md
├── go.mod
├── go.sum
├── Makefile
└── .goreleaser.yml
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.
- 2mo ago First seen · 590 lines · 6,281 tokens per session scan A c7179af2cc81
mcp-unreal CLAUDE.md is an instructions file published in the GitHub repository remiphilippe/mcp-unreal (81 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 6,281 tokens to every session, about $0.0251 per session on Opus 5.5. 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 2026-08-30.
mcp-unreal CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-unreal CLAUDE.mdremiphilippe/mcp-unreal | Instructions file | 81 | 8mo ago | Apache-2.0 | A | 6,281 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |