Search MCP server
{
"mcpServers": {
"parallel-search": {
"type": "http",
"url": "https://search-mcp.parallel.ai/mcp"
}
}
}{
"mcpServers": {
"parallel-search": {
"type": "http",
"url": "https://search-mcp.parallel.ai/mcp"
}
}
}{
"mcpServers": {
"parallel-search": {
"type": "http",
"url": "https://search-mcp.parallel.ai/mcp"
}
}
}{
"servers": {
"parallel-search": {
"type": "http",
"url": "https://search-mcp.parallel.ai/mcp"
}
}
}{
"mcpServers": {
"parallel-search": {
"type": "http",
"url": "https://search-mcp.parallel.ai/mcp"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
A hosted MCP server that provides web search and page fetching capabilities to coding agents. It exposes two tools—web search and URL fetching—with no account or API key required for free-tier use.
- Look up current library or framework documentation while coding without leaving the agent session.
- Verify facts or check the latest release versions of software packages against live web sources.
- Fetch and read the full content of a specific URL to extract details not covered by search result excerpts.
Tools this server exposes
| Tool | Does |
|---|---|
| web_search | Searches the web and returns relevant excerpts with source links. |
| web_fetch | Reads the content of a specified URL and returns it for the agent to use. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.