About Rhoiscribe
Rhoiscribe is a local MCP server and Skill for Hearts of Iron IV modding agents. It combines bundled modding references with tools for generating and checking game-readable files, including path and encoding safeguards.
Key features
- 01Bundled HOI4 prompts and references
- 02Generate and safely edit mod files
- 03cwtools-based language support
- 04Load-risk checks and formatting checks
- 05Cross-IDE agent state and audit logs
Use cases
- 01Generate HOI4 mod content with local guidance
- 02Check files for likely game-loading issues
- 03Make edits that follow mod workspace paths
MCP support
The local stdio MCP server exposes bundled prompts, resources, and modding tools to compatible clients. A Skill package is also available for agents that can read Skill folders.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERHoiScribe
Local MCP server and SKILL for Hearts of Iron IV modding agents
If RHoiScribe helps your modding workflow, starring the repository helps other HOI4 mod authors find it.
RHoiScribe gives Codex, Claude Code, and other MCP-compatible clients a local HOI4 modding reference layer plus tools for generating game-readable files.
The goal is simple: reduce wasted agent work caused by repeated web searches, stale assumptions, unsafe file paths, missing localisation encoding, and Paradox script that looks plausible but does not load in game.
Environment
| Area | Value |
|---|---|
| Server transport | MCP over stdio |
| Implementation | Rust 2024 |
| Build tool | Cargo |
| Primary clients | Codex, Claude Code, MCP-compatible clients |
| Runtime network | Not required for bundled prompts, resources, and tools |
| Modding target | Hearts of Iron IV local mods |
Who It Is For
- Mod authors who want AI agents to generate HOI4 content with better local context.
- Agent workflows that need prompts, resources, and tools available through one MCP server.
- Offline or low-search development sessions where the agent should read bundled HOI4 guidance before writing files.
- Teams that want generated content to follow predictable mod-root paths and reviewable output shapes.
What It Provides
RHoiScribe gives agents a local HOI4 knowledge layer, reusable prompts, and file-oriented tools for common modding work. MCP clients can discover the exact prompts, resources, and tools through the standard MCP list methods after the server is configured.
At a high level, it helps agents with:
- project structure and reference awareness before broad edits
- HOI4 language support based on cwtools
- red/yellow/green checks for load-risk issues before delivery
- fast encoding, formatting, and media convention checks
- safe edits to existing files while respecting workspace conventions
- Rchadow-assisted HOI4 debug launch preparation
- RNMDB-backed cross-IDE agent state under
.rhoiscribe - tool-call audit logs with regex-filtered export from the same state database
- experimental GUI/GFX asset creation when the user approves new procedural art
The bundled Skill package is the quickest way to give compatible agents local access without editing MCP configuration. For complete functionality and a smoother experience, use the MCP server when your agent supports it.
For a closer look at the tools and recommended workflows, read the feature guide. For client configuration, see the MCP setup guide.
Quick Start
Download a prebuilt binary from GitHub Releases:
- Windows:
rhoiscribe-windows-x86_64.exe - Linux:
rhoiscribe-linux-x86_64 - macOS:
rhoiscribe-macos-universal
Warning
The Skill package is still available for now, but it is no longer the recommended path for new language support. That support works best in a long-lived process that can stay warm; Skill runs as short-lived calls, so Skill support will be phased out gradually. Use the MCP server when your client can.
For agents that can read a Skill folder, download the matching Skill package:
- Windows:
rhoiscribe-skill-windows-x86_64.zip - Linux:
rhoiscribe-skill-linux-x86_64.zip - macOS:
rhoiscribe-skill-macos-universal.zip
Unzip it into a stable folder. The package contains SKILL.md and the matching executable, so an agent can use RHoiScribe directly even when you do not want to configure an MCP server.
Keep the downloaded file in a stable folder. On Linux and macOS, run chmod +x on the downloaded file if the system asks for executable permission.
Build from source only when you want a local Cargo build:
cargo build --release
Source builds place the executable under <ABSOLUTE_PATH_TO_RHOISCRIBE>/target/release/.
Print the command path to use in your MCP client:
.\rhoiscribe-windows-x86_64.exe --print-command
Linux and macOS users can run the same option on their downloaded file:
./rhoiscribe-linux-x86_64 --print-command
./rhoiscribe-macos-universal --print-command
For Codex, Claude Code, and generic MCP configuration examples, see docs/client-setup.md.
Help Improve RHoiScribe
HOI4 syntax and modding practice change over time. If you find bundled knowledge that is outdated, incomplete, or wrong, please open an Issue with the game version, file type, source reference, and a minimal example when possible.
Pull requests are welcome for expanding the knowledge catalog, improving examples, or building more MCP tools for generation, validation, project scanning, and other agent workflows.
Attribution
Projects based on RHoiScribe must include a clear README attribution section. Use the short statement template in docs/rhoiscribe-attribution.md.
Acknowledgements
Based on Rchadow
RHoiScribe uses Rchadow, an embeddable Rust playset and launch library for Hearts of Iron IV tools.Rchadow provides playset storage, HOI4 mod discovery, launcher-compatible load file generation, and launch abstractions.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.

