# Sing-box Docs

> Use this tool when you need to semantically search and query documentation for sing-box proxy software, to prevent AI hallucinations and ensure accurate configuration. It takes in documentation inputs, generates embeddings, and outputs relevant search results via stdio or HTTP/SSE transport. Ideal for use cases where reliable and efficient documentation querying is crucial, such as local Claude/Cursor use or Railway cloud deployment.

Canonical page: https://skillsregistry.net/skills/arrteann-singbox  
JSON: https://api.skillsregistry.net/v1/skills/arrteann-singbox

## Description

Sing-box Docs provides a locally-run RAG pipeline for querying sing-box proxy software documentation through semantic search. The system scrapes sing-box documentation, generates SentenceTransformers embeddings indexed with FAISS, and exposes them via an MCP server to prevent AI hallucinations when configuring proxy software. It supports both stdio transport for local Claude/Cursor use and HTTP/SSE transport for Railway cloud deployment.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** devops-ci
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/arrteann-singbox)
- **Repository:** <https://github.com/arrteann/singbox-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "arrteann-singbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/arrteann-singbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/arrteann-singbox/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt