# mcp-web-deepsearch

> mcp-web-deepsearch — noxgle-mcp-web-deepsearch. Use this tool when you need to perform deep web searches with iterative refinement and content extraction, solving problems of accessing hard-to-reach information without requiring API keys. It takes in search queries as input and outputs refined search results and extracted content, interfacing with other MCP agents via stdio or streamable HTTP. Ideal for use cases where comprehensive web search and data extraction are necessary, such as research or data mining tasks.

Canonical page: https://skillsregistry.net/skills/noxgle-mcp-web-deepsearch  
JSON: https://api.skillsregistry.net/v1/skills/noxgle-mcp-web-deepsearch

## Description

MCP server in Docker wrapping WebSearchAgent.py — DuckDuckGo-powered deep web search with iterative refinement and content extraction. No API key required. Works with any MCP agent via stdio or streamable HTTP.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **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/noxgle/mcp-web-deepsearch)

## 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": "noxgle-mcp-web-deepsearch"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/noxgle-mcp-web-deepsearch` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/noxgle-mcp-web-deepsearch/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