mcp-retriever runs on your own machine — the client starts it, so there is no endpoint to ping. 86 installs a week from npm. Last commit 9 Oct 2026.
One MCP server for web search, page extraction, and cited research.
Today is the operative word: we check mcp-retriever every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp-retriever -- npx -y mcp-retriever
{
"mcpServers": {
"mcp-retriever": {
"args": [
"-y",
"mcp-retriever"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-retriever]
command = "npx"
args = ["-y", "mcp-retriever"]
{
"mcpServers": {
"mcp-retriever": {
"args": [
"-y",
"mcp-retriever"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-retriever": {
"args": [
"-y",
"mcp-retriever"
],
"command": "npx"
}
}
}
MCP server for web search and page extraction across the free tiers of several providers
MCP server for web search and page extraction across the free tiers of several providers
AI-powered web research MCP server for agents. Supports web search, browse page, extract...
FastMCP server for Tavily search API with web search and content extraction
Open-source MCP server for AI agents: web search, content extraction, and library docs.
Open-source MCP server for AI agents: web search, content extraction, and library docs.
Web search and page extraction across several independent search providers.
MCP server for web search operations
Answers built from our own checks of this server.