# AskRobots Search

> AskRobots Search is a paid MCP server for web search and scraping. Web search from an independent crawl index, with answers, page and link data. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Paid
- **Starting price:** $25 a month
- **Platforms:** API
- **Website:** https://search.askrobots.com/api
- **Repository:** https://github.com/askrobots/askrobots-search-mcp
- **MCP Registry name:** com.askrobots/search
- **Categories:** web search and scraping
- **Listing updated:** 2026-11-14

## About

Results come from AskRobots' own crawler and index, not a live fetch and not another engine. Safe search is always on.

Seven read-only tools cover more than search. page and site report what the index knows about a URL or website, including health and linking sites, while site flags parked, blocklisted, adult, junk or link-network domains. links lists who links to a page, most trusted first. read returns the stored copy of a page, either the passages answering a query or an outline.

The server is hosted and always needs an API key, sent as a bearer token or X-API-Key; without one it answers 401. Keys are emailed, usually within a day. A keyless trial of 10 searches a day applies to the REST endpoint only.

## Features

- **Own index:** Results come from AskRobots' crawl, not another engine.
- **Search options:** Site, freshness, news, language and verbatim controls.
- **Stored summaries:** answer returns a stored AI summary with numbered sources.
- **Domain signals:** site flags parked, junk or link-network domains.
- **Backlink lookup:** links lists referring sites, up to 50 a call.
- **Directory browse:** Sites by topic ranked by listed-site links.

## Good for

- Give an agent web search without a big-engine key
- Check a domain before citing it
- Find who links to a page
- Read stored page passages

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http search https://search.askrobots.com/api/v1/mcp
```

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

```sh
https://search.askrobots.com/api/v1/mcp
```

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

```json
{
  "mcpServers": {
    "search": {
      "url": "https://search.askrobots.com/api/v1/mcp"
    }
  }
}
```

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

```json
{
  "servers": {
    "search": {
      "type": "http",
      "url": "https://search.askrobots.com/api/v1/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "search": {
      "serverUrl": "https://search.askrobots.com/api/v1/mcp"
    }
  }
}
```

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

```json
{
  "mcpServers": {
    "search": {
      "type": "http",
      "url": "https://search.askrobots.com/api/v1/mcp"
    }
  }
}
```

## Tools

- `search`: Web results with title, URL, snippet and match reasons, plus related searches.
- `answer`: A stored AI summary of a search with numbered sources.
- `page`: What the index knows about a URL, or up to 25.
- `site`: Topic, directory listing, pages indexed, linking sites and flags for a website.
- `links`: Sites linking to a page or site, most trusted first.
- `read`: Stored copy of a page, as passages for a query or an outline.
- `browse_directory`: Directory of sites by topic ranked by links.

## FAQ

### How much does it cost?

$25 a month including 500 searches, then $0.05 a search.

### Can I try it without a key?

Only the REST endpoint, 10 searches a day; MCP needs a key.

### Is safe search on?

Always.

### Is the source public?

No, the repository holds only the registry listing and setup notes.

### Is AskRobots Search free?

No. AskRobots Search is a paid product. Paid plans start at $25 a month.

### How do I add AskRobots Search to Claude Code?

Run this command in your terminal: claude mcp add --transport http search https://search.askrobots.com/api/v1/mcp

### What are the best alternatives to AskRobots Search?

The closest alternatives to AskRobots 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/askrobots-search
