Borrowing it
Nothing to install: this file belongs to ChiR24/Unreal_mcp. 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/ChiR24/Unreal_mcp/dev/AGENTS.mdgit clone --depth 1 https://github.com/ChiR24/Unreal_mcpWrote 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/chir24/unreal_mcp/agents-md)<a href="https://agentmods.dev/instructions/chir24/unreal_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/chir24/unreal_mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.07761 | $0.07761 |
| Opus 5 | $0.03880 | $0.03880 |
| Sonnet 5 | $0.01552 | $0.01552 |
| Haiku 4.5 | $0.00776 | $0.00776 |
Grade A, and why
Unreal_mcp AGENTS.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 7d 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT KNOWLEDGE BASE
MCP tooling for Unreal Engine 5.0-5.8 Preview. Server package version 0.5.30; bridge plugin version 0.5.30 (separate .uplugin). Two user-facing surfaces: a TypeScript stdio MCP server, and the bridge plugin's WebSocket transport and optional native /mcp HTTP/SSE transport.
Area-specific guidance lives in nested AGENTS.md files (see AREA GUIDES below). This root file is the workspace-wide view; do not duplicate their detail here.
STRUCTURE
./
|-- src/ # TypeScript MCP server, NodeNext ESM (strict)
| |-- cli.ts index.ts config.ts constants.ts server-setup.ts # entry + facades
| |-- unreal-bridge*.ts # UnrealBridge (connection/console/properties/system) at src root
| |-- automation/ (45) # WebSocket CLIENT: handshake, request tracking/correlation, frames
| |-- config/ (1) # class-aliases.ts ONLY (DIR; env schema is src/config.ts — name collision)
| |-- gateway/ (4) # gateway manifest DATA + loader; 2 of 4 are *.generated.*
| |-- handlers/ (2) # MCP RESOURCE handlers — NOT tool logic (see tools/handlers)
| |-- resources/ (18) # resource providers behind handlers/ (actors, assets, levels, editor state)
| |-- server/ (13) # SDK construction, stdio lifecycle, tool/resource registry shards
| | |-- gateway/ (27) # gateway search/describe/execute ROUTING — NOT src/gateway
| | `-- mcp-primitives/ (48) # resources/prompts/completions/subscriptions/progress + client profiles, configure store
| |-- services/ (9) # health-monitor, metrics-server (Prometheus), readiness, telemetry
| |-- tools/ # catalog/ (contracts), handlers/<38 domains>/ (action logic),
| | # orchestration/, dynamic/, editor/, level/, schemas/
| | `-- definitions/shared/ # ONLY 2 files (tool-definition.ts, action-sets.ts) — NOT a contract source
| |-- types/ utils/ # utils: commands config interaction logging paths responses serialization validation
|-- plugins/McpAutomationBridge/ # the ONLY plugin; editor-only UE (bridge + native MCP + Fab adapter)
| |-- Source/McpAutomationBridge/{Public (17), Private/}
| | Private/: Core(36) Domains(1120 / 66 domains) Foundation(96) MCP(166) Safety(21) Transport(23) Tests(29) UI(2)
| | Core/: Compatibility Errors Module Requests Security Settings Subsystem
| | MCP/: DynamicTools Execute Gateway Generated Primitives Protocol Registry Resources Routing Tools Transport
| `-- Source/McpAutomationBridgeFab/ # Fab asset-store adapter module (delay-loaded, optional)
| Private/: Fab browser bridge, import watcher, add-to-project, search, details, downloads
|-- tests/ # Vitest unit tests + custom MCP integration runner
|-- scripts/ # generators, packaging, sync, smoke, cleanup
|-- docs/ # handler maps, testing, protocol, plugin extension
`-- .github/workflows/ # pinned CI, release, bump-version, smoke-test (registry/security gates are steps inside ci.yml)
NOTE: src/server/ tool-registry is split (tool-registry.ts + tool-registry-{client,elicitation,gateway,listing,manage-tools}.ts + resource-registry.ts — there is no tool-registry-legacy.ts). src/unreal-bridge*.ts is unreal-bridge.ts + -{connection,console,properties,response,system,types}.ts. The plugin Private/Core/Subsystem/ holds the registration shards; the subsystem .cpp is there (not directly in Core/).
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.
- 7d ago First seen · 227 lines · 7,761 tokens per session scan A df2c39feba80
Unreal_mcp AGENTS.md is an instructions file published in the GitHub repository ChiR24/Unreal_mcp (856 stars, last pushed 2d ago), licensed MIT. It adds 7,761 tokens to every session, about $0.0388 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 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.