Skip to content

ScrapeMole Search

by scrapemole.pages.dev · remote · no sign-in to list tools · v1.0.0 · published by dev.pages.scrapemole

Pay-per-call x402 web search results, news search and search autocomplete suggestions for agents.

Changes · 3
CompareRegistry entry

3 tools: 3 change things.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http search https://search.scrapemole.workers.dev/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

3 tools

Changes things 3Claude Code: ask
  • newsUse for current events, monitoring a company/person/topic in the press, finding recent coverage before answering, or building news digests.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use for current events, monitoring a company/person/topic in the press, finding recent coverage before answering, or building news digests. Returns up to 20 articles with title, direct article url (no redirect wrapper), publisher, published time (ISO 8601), snippet and image when available. sort=date for newest first; freshness=hour|day|week|month to limit age; market for regional editions (en-US, en-GB, de-DE, …). Primary source is Bing News public RSS (retried automatically when Bing answers an empty page), fallback Brave Search News; the response names the source used. Empty results = 404, not charged. Paid tool: x402 USDC on Base, $0.002 per successful call; call without payment to receive the PaymentRequired object.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true
  • suggestUse for keyword research, SEO/content ideas, query expansion before /v1/web or /v1/news, or guessing what people search for around a topic ("how to la" -> "how to lay tile", …).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use for keyword research, SEO/content ideas, query expansion before /v1/web or /v1/news, or guessing what people search for around a topic ("how to la" -> "how to lay tile", …). Returns the completions in source order. lang sets the suggestion language (en, de, fr, es, ja, …). Primary source Google's public suggest endpoint, fallback DuckDuckGo autocomplete; the response names the source used. No suggestions = 404, not charged. Paid tool: x402 USDC on Base, $0.001 per successful call; call without payment to receive the PaymentRequired object.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true
  • webUse when an agent needs to search the web: research, fact finding, finding official pages/docs, competitor or link discovery, grounding an answer with URLs.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Use when an agent needs to search the web: research, fact finding, finding official pages/docs, competitor or link discovery, grounding an answer with URLs. Returns ranked organic results (position, title, url, domain, snippet; published date or lastCrawled time when the source has one). The top 10 come from Bing's public RSS results; deeper pages (count > 10 or page > 1) come from Brave Search. Supports operators the engines support in q (site:, "exact phrase", -exclude, filetype:). If the primary source is unavailable or off-topic it falls back to Brave Search, then the Mwmbl open index; the response says which source answered (source, sourceUrl, fallbackFrom). Pair with ScrapeMole Reader /v1/read to turn a result URL into Markdown. Empty results = 404, not charged. Paid tool: x402 USDC on Base, $0.001 per successful call; call without payment to receive the PaymentRequired object.

    Annotations the server declares

    • readOnlyHint: true
    • openWorldHint: true
    • idempotentHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http search https://search.scrapemole.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__search__web",
      "mcp__search__news",
      "mcp__search__suggest"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as search. Review it before you use it.