# websearch

> websearch — sk-dev-ai-websearch. Use this tool when you need to perform a comprehensive web search across multiple engines, such as DuckDuckGo, Brave, and Google, to find relevant information and merge results with deduplication and ranking. It solves problems of information overload and inconsistent search results by providing a unified and refined output. Ideal for use cases requiring thorough research, fact-checking, or data gathering, with inputs of search queries and outputs of merged and ranked results.

Canonical page: https://skillsregistry.net/skills/sk-dev-ai-websearch  
JSON: https://api.skillsregistry.net/v1/skills/sk-dev-ai-websearch

## Description

Multi-engine web search + fetch MCP server (DDG, Brave, Tavily, Google AI Mode) with consensus-merge dedup, local cross-encoder reranking, and Groq synthesis

## Trust

- **Trust score (0–1):** 0.22
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/SK-DEV-AI/websearch)

## 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": "sk-dev-ai-websearch"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sk-dev-ai-websearch` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sk-dev-ai-websearch/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