# Apfel

> Use this tool when you need to efficiently retrieve and process information from articles or search results while minimizing token output and ensuring SSRF protection. Apfel provides three MCP servers that extract article content, return search results, or combine both, with a focus on reducing overhead and protecting against server-side request forgery. Ideal for applications requiring concise and secure data retrieval, such as chatbots or virtual assistants.

Canonical page: https://skillsregistry.net/skills/arthur-ficial-apfel  
JSON: https://api.skillsregistry.net/v1/skills/arthur-ficial-apfel

## Description

Apfel provides three MCP servers designed for Apple's on-device FoundationModels with a 4096-token context window. apfel-mcp-url-fetch extracts article content via Mozilla Readability capped at ~6000 characters. apfel-mcp-ddg-search returns the top 5 DuckDuckGo results (~300 tokens). apfel-mcp-search-and-fetch combines both in a single call to reduce overhead. All servers emphasize minimal token output and SSRF protection. Available via Homebrew and pip.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** search
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/arthur-ficial-apfel)
- **Repository:** <https://github.com/arthur-ficial/apfel-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": "arthur-ficial-apfel"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/arthur-ficial-apfel` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/arthur-ficial-apfel/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