Cloud MCP Server
SEO data for AI tools
Connect Crawly's MCP server to Claude Code, Claude Desktop, Cursor, Windsurf or Codex. Query domain authority, backlinks and spam scores in plain English - no REST calls, no code.
Get your API key
The MCP server uses the same key as the REST API. One key, both interfaces.
Already have a key? Skip to setup.
Connect your AI tool
Paste your key above and the config snippets below will update instantly - ready to copy or download.
Claude Code
~/.claude/settings.json{
"mcpServers": {
"crawly": {
"type": "http",
"url": "https://www.getcrawly.com/api/mcp?key=crawly_live_your_key"
}
}
}Claude Desktop
~/Library/Application Support/Claude/claude_desktop_config.json{
"mcpServers": {
"crawly": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://www.getcrawly.com/api/mcp?key=crawly_live_your_key"]
}
}
}Cursor
~/.cursor/mcp.json{
"mcpServers": {
"crawly": {
"url": "https://www.getcrawly.com/api/mcp?key=crawly_live_your_key"
}
}
}Windsurf
~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"crawly": {
"serverUrl": "https://www.getcrawly.com/api/mcp?key=crawly_live_your_key"
}
}
}Codex
codex MCP config{
"mcpServers": {
"crawly": {
"type": "http",
"url": "https://www.getcrawly.com/api/mcp?key=crawly_live_your_key"
}
}
}Available tools
Your AI tool calls these automatically based on your question. You never need to invoke them manually.
get_domain_authorityReturns authority score, referring domains, total backlinks, harmonic rank and PageRank for any domain.
| Parameter | Type | Description |
|---|---|---|
| domain | string | The domain to check (e.g. example.com) |
get_backlinksReturns the full backlink profile - referring domains, individual backlinks with quality ratings, and outbound links.
| Parameter | Type | Description |
|---|---|---|
| domain | string | The domain to check (e.g. example.com) |
get_spam_scoreReturns a spam score (0-100) based on link density, IP diversity and authority signals. Lower is better.
| Parameter | Type | Description |
|---|---|---|
| domain | string | The domain to check (e.g. example.com) |
What you can ask
Example prompts
Once connected, just ask your AI tool in plain English.
New to using Crawly with Claude Code? See the step-by-step guide.
›What is the domain authority of nytimes.com?
Calls get_domain_authority and returns the authority score, referring domains and backlink count.
›Who links to ahrefs.com? Show me the top referring domains.
Calls get_backlinks and returns the referring domain list sorted by quality rating.
›Is semrush.com a spammy domain?
Calls get_spam_score and returns a 0-100 risk score with a Low / Medium / High label.
›Compare the authority of moz.com and ahrefs.com
Calls get_domain_authority twice and summarises the scores side by side.
›Find any toxic-looking domains in this list and flag their spam scores
Calls get_spam_score for each domain and highlights anything scoring above 40.
›How many referring domains does my competitor have?
Calls get_domain_authority and pulls referring_domains from the summary.
Limits
| Requests per day | 100 (shared with REST API) |
| Reset | Every 24 hours |
| Shared with | /api/v1/* REST endpoints |
Each MCP tool call counts as one request against your daily quota - the same quota as the REST API.
Also available
REST API
Prefer HTTP? The same data is available as a standard REST API. Same key, same quota - use whichever fits your workflow.
View REST API docs