# AgentShelf DOI Regex Extractor

> AgentShelf DOI Regex Extractor is a paid API for AI agents from agentshelf.syntexa.ch, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-02).

Extracts up to 20 DOI (Digital Object Identifier) matches from a given text string using regex, with no network calls.

## Facts

- Endpoint: POST https://agentshelf.syntexa.ch/v1/regex-doi?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentshelf-doi-regex-extractor-b8502942
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_GpMOpKAcmelsLEAs7H86o

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-doi-regex-extractor-b8502942 -d '<json body>'
```

Example prompt: Extract all the DOI identifiers from this text for me: 'See Smith et al. (2021) doi:10.1038/s41586-021-03819-2 and Jones (2019) https://doi.org/10.1016/j.cell.2019.05.031 for further reading.'

## When to prefer this

Use this endpoint when you need fast, deterministic DOI extraction from text without any network calls or LLM involvement. Prefer the free sandbox endpoint POST /v1/sandbox/regex-doi for testing or when cost avoidance is critical. Choose this paid endpoint for production pipelines where reliability and billing accountability matter. It is ideal for processing academic text, citations, bibliographies, or research paper abstracts in an automated agent workflow.

## Known failure modes

- Empty match list returned and billed if no DOIs are present in the text
- Input text exceeding 100,000 characters is rejected
- Missing or empty 'text' field returns a validation error
- Malformed DOIs that don't match standard regex patterns will not be captured
- Capped at 20 matches — additional DOIs beyond 20 are silently dropped

## How this service works

Call when an agent needs DOI identifiers extracted from text, capped at 20 matches. An empty match list is billed. No network. Exact $0.003 USDC. Prefer unpaid POST /v1/sandbox/regex-doi first.

## Output

A list of up to 20 DOI strings matched by regex from the input text. Returns an empty list if no DOIs are found (note: an empty match list is still billed at $0.003 USDC). No network requests are made during processing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "examples": [
    "10.1000/xyz123"
   ],
   "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-doi-regex-extractor-b8502942/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)