web-retrieval-mcp vs CrawlEyes MCP Server
web-retrieval-mcp is an MCP server published by VelvetSP. Marketplaces we read that list it: 1 (Official MCP Registry). CrawlEyes MCP Server is an MCP server published by waiky-github. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-18. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.
Where each is published
| Marketplace |  web-retrieval-mcp |   CrawlEyes MCP Server |
|---|---|---|
| Official MCP Registry | Listed Version: 0.1.2 Downloads/month (PyPI): 85 Downloads/week (PyPI): 17 Forks (GitHub): 2 Stars (GitHub): 2 Not marked · First seen |
Listed Version: 0.2.0 Downloads/month (PyPI): 126 Downloads/week (PyPI): 34 Forks (GitHub): 0 Stars (GitHub): 2 Not marked · First seen |
Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.
The facts side by side
| Fact | web-retrieval-mcp | CrawlEyes MCP Server |
|---|---|---|
| Marketplaces that list it | 1 | 1 |
| Stars (GitHub) | 2 | 2 |
| Forks (GitHub) (differs) | 2 (better) | 0 (worse) |
| Last release | Not published | Not published |
| Where it runs (differs) | On your machine (web-retrieval-mcp) | On your machine (crawleyes) |
| Transport | stdio | stdio |
| Tools it declares | Not published | Not published |
| Environment variables it asks for (differs) | 2, secrets among them: 2 | 2, secrets among them: 1 |
| Licence | Not stated | Not stated |
| Repository (differs) | github.com/velvetsp/web-retrieval-mcp | github.com/waiky-github/crawleyes |
| Changes in the last 7 days | 0 | 0 |
| First seen | 2026-10-11 | 2026-10-11 |
Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.
What each says it does
web-retrieval-mcp
MCP web search + tiered web fetch for AI agents (Exa, Firecrawl), SSRF-guarded, cross-platform.
CrawlEyes MCP Server
Web scraping & search for AI agents: extract, SearXNG search, rerank, robots compliance. No API key.
How to run each
web-retrieval-mcp As a local MCP server: PyPI package
claude mcp add --env "EXA_API_KEY=<YOUR_EXA_API_KEY>" --env "FIRECRAWL_API_KEY=<YOUR_FIRECRAWL_API_KEY>" --transport stdio web-retrieval-mcp -- uvx web-retrieval-mcpRequires: EXA_API_KEY (secret), FIRECRAWL_API_KEY (secret)
CrawlEyes MCP Server As a local MCP server: PyPI package
claude mcp add --env "TAVILY_API_KEY=<YOUR_TAVILY_API_KEY>" --transport stdio crawleyes -- uvx crawleyesRequires: TAVILY_API_KEY (secret)
Commands built only from what the marketplaces declare; the full set for every client is on each card.
Tools each declares
Neither one's marketplaces publish a list of tools, so there is nothing to compare.
Settings each asks for
Only web-retrieval-mcp asks for
EXA_API_KEY (secret)FIRECRAWL_API_KEY (secret)
Only CrawlEyes MCP Server asks for
SEARXNG_URLTAVILY_API_KEY (secret)
Settings as each marketplace publishes them. Asking for fewer is not better in itself.
What it can do: web-retrieval-mcp · What it can do: CrawlEyes MCP Server · Compare two other plugins
Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.