# Agentshelf Markdown Link Extractor

> Agentshelf Markdown Link Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-02).

Extracts all markdown hyperlinks (up to 20) from a given text string using regex, returning matched link text and URLs.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/regex-markdown-link?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-markdown-link-extractor-ca122718
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_leEKRxMjy6ZW2Ut2kmTFT

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentshelf-markdown-link-extractor-ca122718 -d '<json body>'
```

Example prompt: Can you extract all the markdown links from this text: 'Check out [OpenAI](https://openai.com) and [GitHub](https://github.com) for more info — also see [our docs](https://docs.example.com/start).'

## When to prefer this

Use this endpoint when you need fast, deterministic regex-based extraction of markdown hyperlinks from text without any LLM or network calls. Ideal for pipelines that process markdown documents, READMEs, or agent-generated reports where you need a structured list of links quickly and cheaply. Prefer the free sandbox POST /v1/sandbox/regex-markdown-link endpoint for testing before committing to paid calls.

## Known failure modes

- Empty match list returned with charge if no markdown links exist in the text
- Text exceeds 100,000 character limit — request rejected
- Text is empty or missing — request rejected
- More than 20 links present — only first 20 matches returned, remainder silently truncated
- Malformed markdown links (e.g. missing closing parenthesis) may not be matched by regex

## How this service works

Call when an agent needs markdown links extracted from text, capped at 20 matches. An empty match list is billed. No network. Exact $0.001 USDC. Prefer unpaid POST /v1/sandbox/regex-markdown-link first.

## Output

Returns a list of up to 20 matched markdown links found in the input text, each containing the link label/text and the target URL. An empty list is returned (and still billed) if no markdown links are found.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "[hello](https://example.com)"
   ],
   "maxLength": 100000,
   "minLength": 1,
   "description": "Input for this SKU. The route description says whether it is plain text, a URL, base64 bytes, or an already-encoded token."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentshelf-markdown-link-extractor-ca122718/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentshelf.syntexa.ch](https://www.zero.xyz/host/agentshelf.syntexa.ch/llms.txt)