# AfterImage MCP Web Page Search and Fetch

> AfterImage MCP Web Page Search and Fetch is a paid API for AI agents from afterimage.page, paid per call via x402, $0.002/call, status unknown (last checked 2026-09-14).

Provides MCP-compatible tools to search AfterImage's cached page corpus and fetch any public URL (returning cached copy if available, otherwise live fetching).

## Facts

- Endpoint: POST https://afterimage.page/mcp
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/afterimage-mcp-web-page-search-and-fetch-d69cc600
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_dWF8c3i748cF0JsKWXrSP

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 afterimage-mcp-web-page-search-and-fetch-d69cc600 -d '<json body>'
```

Example prompt: Search AfterImage's cached page corpus for pages about 'climate policy 2024', and if you don't find what I need, fetch the live page at https://example.com/climate-policy and return its content with the timestamp and hash.

## When to prefer this

Choose this endpoint when you need MCP-native tools for web page retrieval with built-in caching and deduplication — especially when you want to reuse a previously fetched copy (with provenance metadata like timestamp and SHA-256) rather than always hitting the live web. Prefer it when corpus search (no live web traffic) is sufficient, or when you want transparent caching behavior integrated with an MCP workflow.

## Known failure modes

- URL not publicly accessible — live fetch fails with connectivity or permission error
- search_pages returns empty results if query matches nothing in the corpus
- invalid or malformed URL causes get_page to error
- rate limiting or payment failure blocks the request at $0.002 USDC per call
- private or paywalled pages cannot be fetched even via live mode

## How this service works

MCP tools: search_pages (corpus only) and get_page (any public URL).

## Output

For search_pages: a list of matching cached pages from AfterImage's corpus with URLs and relevant snippets, without making any live web requests. For get_page: the full content of the requested URL — either a cached copy (with original fetch timestamp and SHA-256 hash) or a freshly fetched live version if not yet in the corpus.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/afterimage-mcp-web-page-search-and-fetch-d69cc600/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from afterimage.page](https://www.zero.xyz/host/afterimage.page/llms.txt)