HOI4 Agent Tools
A source-preserving MCP server for coding agents working on Hearts of Iron IV mods, combining focus tree, GUI, and map tools with transaction safety.
README
HOI4 Agent Tools
HOI4 Agent Tools is a source-preserving Model Context Protocol server for coding agents working on Hearts of Iron IV mods. It combines a Focus Tree Workbench, Scripted GUI Studio, and headless map transaction system over one shared parser, workspace index, renderer, artifact store, and rollback engine.
The workflow is:
human request → coding agent → MCP tools → registered external mod workspace
The MCP server is the product interface. There is no focus editor, GUI editor, map editor, dashboard, or gameplay-tool CLI. The setup utility only creates server configuration, checks dependencies, and prints client configuration for review.
Install
Requires Node.js 22 or 24.
npm install --global hoi4-agent-tools@0.1.0
hoi4-agent-tools-setup --init-config /path/to/config.json --workspace /path/to/mod --game /path/to/game
hoi4-agent-tools-setup --diagnose --config /path/to/config.json
hoi4-agent-tools-setup --print-client-config --config /path/to/config.json
The generated configuration is read-only. Add --enable-writes --server-state /separate/operator/state only when transaction apply/rollback is intended. The state root is mandatory in transaction mode and must not overlap source, registration, artifact, cache, fixture, or generated-storage roots. The utility never edits an MCP client's settings.
For one-shot stdio installation, clients can launch:
npx -y hoi4-agent-tools@0.1.0
with HOI4_AGENT_CONFIG set to the reviewed config path.
Minimal configuration
{
"version": 1,
"writePolicy": "read-only",
"registrationRoots": ["/projects/hoi4-mods"],
"writableRegistrationRoots": [],
"workspaces": [
{
"id": "my_mod",
"name": "My Mod",
"root": "/projects/hoi4-mods/my-mod",
"gameRoot": "/games/Hearts of Iron IV",
"dependencyRoots": [],
"replacePaths": [],
"writeEnabled": false
}
]
}
All public paths are workspace-relative. Installed game and dependency roots are always read-only. Runtime mod registration additionally requires a separate, default-empty writableRegistrationRoots capability, so a read-only source root cannot be relabelled as a mod. Caches, render evidence, transaction manifests, and rollback blobs live under the workspace's ignored .hoi4-agent/ directory; the private journal-authentication key and replay-protection heads live only under the separate operator serverStateRoot.
See configuration and security before enabling writes.
Client configuration
Generic JSON-based clients:
{
"mcpServers": {
"hoi4_agent_tools": {
"command": "npx",
"args": ["-y", "hoi4-agent-tools@0.1.0"],
"env": { "HOI4_AGENT_CONFIG": "/absolute/path/to/config.json" }
}
}
}
Codex config.toml:
[mcp_servers.hoi4_agent_tools]
command = "npx"
args = ["-y", "hoi4-agent-tools@0.1.0"]
env = { HOI4_AGENT_CONFIG = "/absolute/path/to/config.json" }
On Windows, use npx.cmd. Additional reviewed examples are under examples/clients.
Safe write protocol
The server starts read-only. A source write requires all of the following:
- global transaction writes enabled with an isolated persistent
serverStateRoot; - a registered workspace whose canonical root is allowlisted and write-enabled;
- a completed in-memory dry run with all affected files and validation results;
- a persisted transaction ID and plan hash;
- human approval through the coding-agent client;
- a separate
hoi4.transaction_applycall carrying the exact expected plan hash.
Apply rechecks the principal, workspace, canonical roots, expiry, and every source hash. Stale or cross-workspace plans are rejected. Multi-file changes use a durable journal and exact rollback blobs; post-write validation failure restores the original bytes. See transactions.
Tool families
- Projects:
hoi4.project_register,hoi4.project_scan,hoi4.project_status - Focus: scan, import, lint, layout, render, plan changes, and export
- GUI: scan, lint, deterministic render/state matrix, compare, and plan changes
- Map: scan, inspect, allocate, plan, render, and validate
- Transactions:
hoi4.transaction_diff,hoi4.transaction_apply,hoi4.transaction_rollback,hoi4.transaction_status - Artifacts:
hoi4.artifact_list,hoi4.artifact_describe, plus opaque MCP resources
Large HTML, SVG, PNG, JSON, fidelity, hierarchy, map, and diff outputs are resources rather than oversized tool responses. MCP prompts guide safe focus, GUI, and map workflows but never bypass validation.
Offline rendering boundary
Scripted GUI Studio parses and renders source files itself. It never launches, controls, automates, hooks, or captures screenshots from Hearts of Iron IV. Every GUI render is labelled as an offline representation and includes a fidelity report with modelled, approximated, ignored, missing, unsupported, and unresolved fields.
Streamable HTTP
hoi4-agent-tools-http provides stateful Streamable HTTP on 127.0.0.1 by default. Every request requires authentication. Non-loopback deployment additionally requires HTTPS, OAuth/OIDC JWT verification, allowed origins, Host validation, principal-to-workspace grants, and limits. See self-hosting; legacy SSE-only transport is not provided.
Documentation
- Documentation index
- Architecture
- Focus workflow
- GUI workflow and fidelity
- Map workflow
- Testing and fixtures
- Compatibility
- Known limitations
- Release and Registry publication
Development
npm ci
npm run check
npm run inspector
Portable CI uses only project-owned synthetic fixtures. Opt-in local integration tests may read installed game and external mod sources but never copy or modify them.
Apache-2.0 licensed. Hearts of Iron IV and Paradox Interactive are trademarks of their respective owners; this project is unaffiliated.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。