Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "search": {
      "type": "http",
      "url": "https://search.scrapemole.workers.dev/mcp"
    }
  }
}

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

[mcp_servers.search]
url = "https://search.scrapemole.workers.dev/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "search": {
      "type": "remote",
      "url": "https://search.scrapemole.workers.dev/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "search": {
      "type": "http",
      "url": "https://search.scrapemole.workers.dev/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=search&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vc2VhcmNoLnNjcmFwZW1vbGUud29ya2Vycy5kZXYvbWNwIn0%3D"
}

{
  "servers": {
    "search": {
      "type": "http",
      "url": "https://search.scrapemole.workers.dev/mcp"
    }
  }
}

{
  "mcpServers": {
    "search": {
      "httpUrl": "https://search.scrapemole.workers.dev/mcp"
    }
  }
}

extensions:
  "search":
    enabled: true
    name: "search"
    type: streamable_http
    uri: "https://search.scrapemole.workers.dev/mcp"
    timeout: 300

Quality 81 / 100new

protocol75 · weight 25

warn
protocol.modernnewest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
n/a
protocol.statelessonly applies to 2026-07-28 servers
pass
protocol.transportstreamable HTTP
n/a
protocol.list_ttlonly applies to 2026-07-28 servers

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene86 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations3 of 3 tools declare readOnlyHint or destructiveHint
fail
tools.directory_hintsno tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: web (destructiveHint); suggest (destructiveHint); news (destructiveHint)
pass
tools.token_costabout 1,028 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stabilityn/a · weight 15

n/a
stability.changes, stability.rug_pulltool history recorded for 6 of the 7 days needed

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvableno npm or PyPI package

3 tools, about 1,028 tokens to load them all · tool set d0bf047bf832 · tools last changed 2026-10-13 · checked 2026-10-20 10:35 UTC

Tool changes

2026-10-13webchangeddescription
before
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, $0.002 per successful call; call without payment to receive the PaymentRequired object.
after · 98% of words in common
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.

Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 83 / 100

no-repository

provenance55

liveness100

freshness100

hygiene80

+dns-namespace +website +reachable +uptime-100% +updated-7d-ago -no-repository

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://search.scrapemole.workers.dev/mcp` streamable-http	none	yes	100%	300 ms	2025-06-18	2026-10-20

Tools (3)

`news`read-only	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.
`suggest`read-only	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.
`web`read-only	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.

Schemas: list_tools.

More from dev.pages.scrapemole

And 5 more from this publisher.

Official server.json

{
  "name": "dev.pages.scrapemole/search",
  "title": "ScrapeMole Search",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://search.scrapemole.workers.dev/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "1.0.0",
  "websiteUrl": "https://scrapemole.pages.dev",
  "description": "Pay-per-call x402 web search results, news search and search autocomplete suggestions for agents."
}