IntuneRosetta-mcp
Translates raw OMA-URI/CSP path strings into structured, human-readable Intune policy metadata, and enables search and resolution of policy names to CSP keys.
README
IntuneRosetta-mcp
A Model Context Protocol (MCP) server that translates raw OMA-URI / CSP path strings into structured, human-readable Intune policy metadata — search 800+ pre-built policy records and resolve human-readable names to CSP keys, all from your AI assistant.
Quick start
No local installation required. Use npx to run the server on-demand:
npx github:UniverseCitiz3n/IntuneRosetta-mcp
Prerequisites: Node.js ≥ 18 and
gitavailable on your PATH environment variable.
Install in your MCP client
VS Code (GitHub Copilot)
Install with one click:
| Platform | VS Code | VS Code Insiders |
|---|---|---|
| macOS / Linux | ||
| Windows |
Or add manually to .vscode/mcp.json in your workspace (create the file if it doesn't exist):
{
"servers": {
"intunerosetta": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:UniverseCitiz3n/IntuneRosetta-mcp"]
}
}
}
Claude Desktop
Edit your Claude Desktop config file:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"intunerosetta": {
"command": "npx",
"args": ["-y", "github:UniverseCitiz3n/IntuneRosetta-mcp"]
}
}
}
Claude Code
Add to your project's mcp.json file:
{
"mcpServers": {
"intunerosetta": {
"command": "npx",
"args": ["-y", "github:UniverseCitiz3n/IntuneRosetta-mcp"]
}
}
}
GitHub Copilot Coding Agent (repository settings)
In your repository's Settings → Copilot → MCP servers, add:
{
"mcpServers": {
"intunerosetta": {
"type": "local",
"command": "npx",
"args": ["-y", "github:UniverseCitiz3n/IntuneRosetta-mcp"],
"tools": ["*"]
}
}
}
Available tools
| Tool | Input | Description |
|---|---|---|
translate_csp_key |
key (string) |
Translates a raw underscore-delimited OMA-URI / CSP path string into structured, human-readable policy metadata |
batch_translate |
keys (string[]) |
Translates an array of CSP path strings in one call |
search_policy |
query (string), limit (number, optional) |
Fuzzy keyword search across the policy database by name, description, category, or CSP path fragment |
resolve_to_csp |
query (string), limit (number, optional) |
Resolves a human-readable policy name or keyword to matching CSP key(s) and full metadata |
extract_and_translate |
text (string) |
Extracts all OMA-URI/CSP paths from a block of freeform text (Event Viewer XML, MDM diagnostic output, JSON exports, log files) and translates each one. Returns resolved policy metadata and a list of unrecognised paths |
suggest_policy |
goal (string), context (string, optional), limit (number, optional) |
Given a plain-English security or configuration goal, returns matching CSP policies with recommended production values and reasoning |
refresh_kb |
force (boolean, optional) |
Rebuilds the local KB by querying msgraph-kb with all predefined search terms. Requires MSGRAPH_KB_COMMAND to be set |
Example usage
Translate a raw CSP key
translate_csp_key("device_vendor_msft_policy_config_defender_attacksurfacereductionrules_blockexecutionofpotentiallyobfuscatedscripts_2")
Returns:
{
"name": "Block execution of potentially obfuscated scripts",
"description": "This rule detects suspicious properties within an obfuscated script.",
"value": "2",
"csp_path": "./Device/Vendor/MSFT/Policy/Config/Defender/AttackSurfaceReductionRules",
"category": "Defender ASR",
"docs_url": "https://learn.microsoft.com/en-us/windows/security/threat-protection/microsoft-defender-atp/attack-surface-reduction"
}
Search for a policy by keyword
search_policy("bitlocker startup authentication")
Resolve a human-readable name to CSP key
resolve_to_csp("block obfuscated scripts")
msgraph-kb integration (optional)
IntuneRosetta can connect to the msgraph-kb MCP server to enrich its local knowledge base with live Microsoft Graph API metadata.
Set the following environment variables to enable this integration:
| Variable | Description | Example |
|---|---|---|
MSGRAPH_KB_COMMAND |
Executable used to launch the msgraph-kb server | node or npx |
MSGRAPH_KB_ARGS |
Space-separated arguments passed to the command | /path/to/msgraph-kb/dist/index.js |
When MSGRAPH_KB_COMMAND is set, IntuneRosetta automatically queries msgraph-kb in the background at startup and populates any missing records in the local database. You can also trigger a manual refresh at any time with the refresh_kb tool.
Example — VS Code with msgraph-kb integration:
{
"servers": {
"intunerosetta": {
"type": "stdio",
"command": "npx",
"args": ["-y", "github:UniverseCitiz3n/IntuneRosetta-mcp"],
"env": {
"MSGRAPH_KB_COMMAND": "npx",
"MSGRAPH_KB_ARGS": "-y github:UniverseCitiz3n/msgraph-kb-mcp"
}
}
}
}
Local development
Clone the repo, install dependencies, and build:
git clone https://github.com/UniverseCitiz3n/IntuneRosetta-mcp.git
cd IntuneRosetta-mcp
npm install
npm run build
node dist/index.js
Point any MCP client at the built binary:
{
"mcpServers": {
"intunerosetta": {
"command": "node",
"args": ["/absolute/path/to/IntuneRosetta-mcp/dist/index.js"]
}
}
}
Run tests:
npm test
How it works
At startup the server seeds an in-memory SQLite database from a pre-built knowledge base (db/intune-policies.json, 800+ records covering Windows, Linux, and Apple ADE) and applies a set of hand-curated seed records on top. Records include:
normalized_key— underscore-delimited CSP path (lowercase,device_vendor_msft_prefix stripped)name/description— human-readable label and explanationcsp_path— canonical OMA-URI path (e.g../Device/Vendor/MSFT/Policy/Config/Defender/AttackSurfaceReductionRules)category— policy area (e.g.Defender ASR,BitLocker,LAPS)docs_url— link to Microsoft documentationvalue_map— map of raw integer values to human-readable labels (e.g.{"0":"Disabled","1":"Block","2":"Audit"})
When a translate_csp_key or search_policy call arrives, the server looks up the normalized key in SQLite, attaches the decoded value label, and returns structured PolicyMetadata.
If MSGRAPH_KB_COMMAND is configured, a background KB build queries the msgraph-kb MCP server with 20 predefined Intune-related search terms and upserts any new results into the local database — no manual curation required for Graph API endpoints.
Contributing to the DB
The pre-built knowledge base lives in db/intune-policies.json. If you know
of a missing or incorrect policy record you can contribute it via a pull
request — see db/CONTRIBUTING.md for full
instructions, field definitions, and validation rules.
In short:
- Copy
db/contribution-template.json→db/contributions/<your-file>.json - Fill in your records (required:
normalized_key,name,csp_path,category) - Run
node scripts/validate-contributions.jslocally to check for errors - Open a PR — CI validates the file automatically
License
ISC
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。