canonical: https://jentic.com/apis/clawfetch.ai/clawfetch

# ClawFetch

The ClawFetch API turns the open web into agent-ready data. It fetches any URL with stealth page fetching, renders JavaScript-heavy pages in a headless browser, and extracts typed JSON from specialized site extractors such as GitHub, YouTube, and Wikipedia. It also runs multi-source web research across a topic or company, parses documents, and screens domain name availability with live WHOIS. There is no account or API key: calls are paid per request in USDC through the x402 protocol.

## For AI agents

Fetch and render web pages, extract typed JSON from specialized site extractors, run web research, and screen domains, across 9 keyless endpoints paid per request.

## Scope

Does not store crawled data long term, run scheduled crawl jobs, or manage proxy pools. Use for on-demand web fetching, rendering, extraction, research, and domain screening only.

## Capabilities

- Fetch any URL with stealth page fetching, or render a JavaScript-heavy page in a headless browser
- Extract typed, structured JSON from specialized site extractors
- Run multi-source web research across a topic or company
- Check bulk domain name availability and brainstorm available names with live WHOIS
- Parse a document and list the available extractors

## Use cases

### Agent-Ready Web Fetching

Give an agent clean data from pages that normally block or require JavaScript. The agent fetches a URL with stealth fetching, renders a single-page app in a headless browser when needed, and pulls typed JSON from a specialized extractor instead of raw HTML. This hands the model structured fields rather than a page it must parse.

Example prompt: Render a JavaScript-heavy page, then extract structured JSON from it

### Research and Domain Screening

Gather intelligence and check names in one place. The agent runs multi-source research on a company or topic, parses a supporting document, and screens candidate domain names for availability with live WHOIS. The research and domain operations return structured results an agent can rank.

Example prompt: Run research on a company, then check availability for a list of candidate domains

### AI Agent Integration via Jentic

An AI agent discovers and calls ClawFetch through Jentic. The agent searches by intent, receives the matching operation and its input schema, and fetches or extracts a page. Because ClawFetch is keyless and paid per request, the agent calls it directly through your own instance with nothing to configure first.

Example prompt: Search Jentic for 'fetch a web page', load the operation schema, and fetch the URL

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| POST | `/fetch` | Fetch a URL with stealth page fetching |
| POST | `/render` | Render a JavaScript-heavy page in a headless browser |
| POST | `/extract` | Extract typed JSON from a specialized site extractor |
| POST | `/research` | Run multi-source web research |
| POST | `/domains/check` | Check bulk domain availability via WHOIS |
| GET | `/extractors` | List the available structured-data extractors |

## Key resources

- **Fetch and Render** — Stealth URL fetching and headless rendering for JavaScript-heavy pages
- **Extract** — Typed JSON extraction from specialized site extractors, listed by the extractors operation
- **Research** — Multi-source web research and document parsing
- **Domains** — Bulk domain availability checks and name brainstorming via live WHOIS

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 68 / 100
- **Maturity:** AI-Aware
- **Dimensions:**
  - Foundational Compliance: 78 / 100
  - Developer Experience & Jentic Compatibility: 52 / 100
  - AI-Readiness & Agent Experience: 52 / 100
  - Agent Usability: 94 / 100
  - Security: 100 / 100
  - AI Discoverability: 92 / 100
- **View full report:** https://jentic.com/apis/clawfetch.ai/clawfetch/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring ClawFetch by hand means handling x402 USDC micropayments on Base and the stealth-fetch and extraction request shapes yourself. Through Jentic you install once, import ClawFetch from the API Directory, and your agent calls it directly, with no key to create.
- **Permission scoping:** ClawFetch needs no key, and through Jentic you still choose which of its operations your agent may call, such as fetching and extracting pages, while leaving the domain availability lookups out of the set.
- **Credential handling:** ClawFetch needs no API key, account, or subscription: it charges per request in USDC through the x402 protocol, so there is no secret for Jentic to hold. Your agent calls it directly through your own Jentic One instance.
- **Discovery method:** Agents search Jentic by intent such as 'fetch a web page' or 'extract structured data', and Jentic returns the matching ClawFetch operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Firecrawl** — Crawling and extraction that returns clean markdown or JSON, like ClawFetch's fetch and extract operations.
- **Apify** — A platform of hosted scrapers and actors, versus ClawFetch's direct fetch, render, and extract calls.
- **Bright Data** — Proxy networks and large-scale collection that can sit behind heavier scraping than ClawFetch handles alone.

## FAQ

### What authentication does the ClawFetch API use?

The ClawFetch API requires no API key, account, or subscription, per its OpenAPI spec. Calls are paid per request in USDC through the x402 protocol instead. Through Jentic your agent calls it directly from your own instance, with nothing to register first.

### Is there a ClawFetch MCP server?

You do not need a separate MCP server to give your agent ClawFetch. Jentic connects it directly from the API Directory: import it, and your agent calls its fetch, render, and extract operations on demand. Operations are discovered as needed, so no extra server's tool definitions load into the agent's context.

### Can I extract structured data from a page with the ClawFetch API?

Yes. Call the extract operation to get typed JSON from a specialized site extractor, or render a JavaScript-heavy page first and then extract from it. The extractors operation lists which specialized sites are supported.

### Can I limit what my agent is allowed to do with the ClawFetch API?

Yes. ClawFetch needs no key, and because you run Jentic One yourself your rules still decide which operations the agent may call. You can allow fetching and extracting pages while withholding the domain availability lookups, and every call is logged.

### What are the rate limits for the ClawFetch API?

The OpenAPI spec does not specify rate limits; ClawFetch is pay-per-request in USDC through the x402 protocol, with no account tier to exceed. See the ClawFetch documentation at https://clawfetch.ai for current terms.

### How do I fetch a web page with the ClawFetch API through Jentic?

Search Jentic for 'fetch a web page' to get the matching ClawFetch operation and its input schema, then your agent passes the URL and reads the returned content. To run it on your own infrastructure, install Jentic One from its GitHub repo.