Captcha-avoiding web, news, image and video search plus page fetching over free sources
Connect Runs on your machine
claude mcp add multi-websearch-mcp -e WEBSEARCH_UA=<WEBSEARCH_UA> -e SEARXNG_URL=<SEARXNG_URL> -e WEBSEARCH_MCP_PAID=<WEBSEARCH_MCP_PAID> -- uvx multi-websearch-mcp==0.3.0rc2
{
"mcpServers": {
"multi-websearch-mcp": {
"command": "uvx",
"args": [
"multi-websearch-mcp==0.3.0rc2"
],
"env": {
"WEBSEARCH_UA": "<WEBSEARCH_UA>",
"SEARXNG_URL": "<SEARXNG_URL>",
"WEBSEARCH_MCP_PAID": "<WEBSEARCH_MCP_PAID>"
}
}
}
}
{
"mcpServers": {
"multi-websearch-mcp": {
"command": "uvx",
"args": [
"multi-websearch-mcp==0.3.0rc2"
],
"env": {
"WEBSEARCH_UA": "<WEBSEARCH_UA>",
"SEARXNG_URL": "<SEARXNG_URL>",
"WEBSEARCH_MCP_PAID": "<WEBSEARCH_MCP_PAID>"
}
}
}
}
{
"servers": {
"multi-websearch-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"multi-websearch-mcp==0.3.0rc2"
],
"env": {
"WEBSEARCH_UA": "<WEBSEARCH_UA>",
"SEARXNG_URL": "<SEARXNG_URL>",
"WEBSEARCH_MCP_PAID": "<WEBSEARCH_MCP_PAID>"
}
}
}
}
Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.
Tools
This server runs locally, so its tools are listed by your MCP client once it starts.
Environment variables
| Name | Description |
|---|---|
WEBSEARCH_UARequired | User-Agent with your contact (e-mail or URL), e.g. 'websearch/0.3 ([email protected])'; Wikimedia, GDELT and Hacker News ask for it |
SEARXNG_URLOptional | Your SearXNG instance (default http://127.0.0.1:8888); without it the feeds and APIs still answer |
WEBSEARCH_MCP_PAIDOptional | 0 = agents may never use paid APIs |
Details
| Package | [email protected] (PYPI, stdio) |
| First published | 16 Nov 2026 |
| Last updated | 16 Nov 2026 |
| Registry name | io.github.c0decave/multi-websearch-mcp |
More search and web servers See all
Listing data from the official MCP registry. Status and tools from NestDaddy's daily check. Browse all MCP servers.
