# local-websearch

> local-websearch — bennmann-local-websearch. Use this tool when you need to perform private web searches or automate query tasks without relying on external search engines. It solves problems related to secure and self-contained information retrieval, providing outputs in a standardized format. The local-websearch tool accepts search queries as input and returns relevant results via the MCP stdio protocol.

Canonical page: https://skillsregistry.net/skills/bennmann-local-websearch  
JSON: https://api.skillsregistry.net/v1/skills/bennmann-local-websearch

## Description

A local DuckDuckGo web search MCP server. Exposes two tools via the MCP stdio protocol. Attempts to self rate-limit.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** search
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/bennmann/local-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": "bennmann-local-websearch"
    }
  }
}
```

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