Common Crawl's public web archive — find every time a URL was crawled since 2008 and read the exact page bytes that were captured.
Setup
Choose your client, copy the config, then fill in any required environment variables.
claude mcp add --transport http commoncrawl https://gateway.pipeworx.io/commoncrawl/mcp~/.codex/config.toml
[mcp_servers.commoncrawl]
url = "https://gateway.pipeworx.io/commoncrawl/mcp"
# codex mcp add commoncrawl --url https://gateway.pipeworx.io/commoncrawl/mcp~/.cursor/mcp.json
{
"mcpServers": {
"commoncrawl": {
"url": "https://gateway.pipeworx.io/commoncrawl/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"commoncrawl": {
"type": "http",
"url": "https://gateway.pipeworx.io/commoncrawl/mcp"
}
}
}~/.gemini/settings.json
{
"mcpServers": {
"commoncrawl": {
"httpUrl": "https://gateway.pipeworx.io/commoncrawl/mcp"
}
}
}claude_desktop_config.json · Customize › Connectors › Add custom connector
{
"mcpServers": {
"commoncrawl": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://gateway.pipeworx.io/commoncrawl/mcp"
]
}
}
}.trae/mcp.json
{
"mcpServers": {
"commoncrawl": {
"url": "https://gateway.pipeworx.io/commoncrawl/mcp"
}
}
}