# Faceabot Deep search

> Faceabot Deep search is a free MCP server for web search and scraping. Free multi-source research search across papers, news, archives, code and forums. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Free
- **Platforms:** API
- **Website:** https://faceabot.com/tools/com.faceabot/deep-search
- **MCP Registry name:** com.faceabot/deep-search
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-15

## About

Instead of hitting one search engine, this server runs a single question against sources that general web search tends to miss. Scientific papers come from arXiv and Crossref, news from GDELT across 100-plus languages for roughly the last three months, and further results from the Internet Archive, GitHub repositories and Wikipedia.

It also looks at what people say in public communities such as Bluesky, Mastodon, Lemmy, Hacker News and forums. Results are dated and linked, and only official free access routes are used. A hosted endpoint means there is nothing to install.

Faceabot publishes a measured-reliability page for it: 488 checks logged, all succeeded, and its read-only test call to list_deep_sources has returned a real result every time.

## Features

- **Papers and preprints:** Searches arXiv and Crossref for scientific work.
- **Multilingual news:** Covers world news from the last three months in 100+ languages via GDELT.
- **Archive and code results:** Includes the Internet Archive and GitHub repositories.
- **Community voices:** Surfaces posts from Bluesky, Mastodon, Lemmy, Hacker News and forums.
- **Dated, linked output:** Each result carries a date and a link back to its source.

## Good for

- Background research that mixes papers and news
- Check what developers are saying about a library
- Find archived copies of a vanished page
- Gather public opinion on a topic across communities

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http deep-search https://faceabot.com/tools-mcp/deep-search
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://faceabot.com/tools-mcp/deep-search
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "deep-search": {
      "url": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "deep-search": {
      "type": "http",
      "url": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "deep-search": {
      "serverUrl": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "deep-search": {
      "type": "http",
      "url": "https://faceabot.com/tools-mcp/deep-search"
    }
  }
}
```

## Tools

- `list_deep_sources`: Lists the sources the deep search covers; used for Faceabot's own reliability checks.

## FAQ

### Does it need an API key?

No. It is free and keyless; add the hosted URL to your client's MCP config.

### Is it remote or local?

Remote only. The server is hosted over Streamable HTTP, so there is nothing to install.

### How reliable is it?

Faceabot's own monitoring shows 488 of 488 checks succeeded as of 2026-11-15.

### Is Faceabot Deep search free?

Yes. Faceabot Deep search is free to use.

### How do I add Faceabot Deep search to Claude Code?

Run this command in your terminal: claude mcp add --transport http deep-search https://faceabot.com/tools-mcp/deep-search

### What are the best alternatives to Faceabot Deep search?

The closest alternatives to Faceabot Deep search are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.

## Alternatives

- [Scrapling MCP Server](https://ai-powered.com/mcp/scrapling-mcp-server): Scrapling MCP Server is an open-source MCP server for web search and scraping.
- [Firecrawl MCP Server](https://ai-powered.com/mcp/firecrawl-mcp-server): Firecrawl MCP Server is a freemium MCP server for web search and scraping.
- [SearXNG Search](https://ai-powered.com/mcp/searxng-search): SearXNG Search is an open-source MCP server for web search and scraping.
- [NeuralVerge](https://ai-powered.com/mcp/neuralverge): NeuralVerge is an MCP server for web search and scraping.
- [AI-Powered directory](https://ai-powered.com/mcp/ai-powered-directory): AI-Powered directory is a free MCP server for developer tools.
- [Shopify MCP Server (any store)](https://ai-powered.com/mcp/shopify-mcp-server-any-store): Shopify MCP Server (any store) is a paid MCP server for e-commerce.
- [Chanroll: YouTube Channel Video Scraper (Official API)](https://ai-powered.com/mcp/chanroll-youtube-channel-video-scraper-official-api): Chanroll: YouTube Channel Video Scraper (Official API) is a paid MCP server for design and media.
- [Vidvett: YouTube Video Details Scraper (Official API)](https://ai-powered.com/mcp/vidvett-youtube-video-details-scraper-official-api): Vidvett: YouTube Video Details Scraper (Official API) is a paid MCP server for design and media.

---
Source: https://ai-powered.com/mcp/faceabot-deep-search
