Parallel Search MCP server

Exposes Parallel's Search and Extract APIs as web_search and web_fetch tools: objective-driven web search and token-efficient markdown extraction from URLs, with excerpts capped near 25,000 characters per call. Free anonymously at fast-mode rate limits; an API key bearer token or the separate /mcp-oauth endpoint raises limits and unlocks search-setting overrides.

Endpoint and access

No sign-in: your client connects and lists tools immediately, with no account or key.

No sign-inEndpoint checked 2026-10-05Operated by Parallel AI

MCP endpoint (Streamable HTTP)

https://search.parallel.ai/mcp

Vendor documentation

What you can do with it

Run objective-driven web searches inside an agent loop.
Fetch markdown excerpts from specific URLs after searching.
Pin search mode, location, or domain policy via URL parameters.
Verify facts against current web sources during a conversation.

Tools advertised by the last live check:

web_search
web_fetch

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers a Streamable HTTP server. Use --scope project to write .mcp.json for the repo.

Claude Code configuration

claude mcp add --transport http parallel-search https://search.parallel.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).

Codex configuration

codex mcp add parallel-search --url https://search.parallel.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable parallel-search in your MCP settings.

Cursor configuration

{
  "mcpServers": {
    "parallel-search": {
      "url": "https://search.parallel.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure). The type must be streamableHttp for a remote HTTP server.

Cline configuration

{
  "mcpServers": {
    "parallel-search": {
      "type": "streamableHttp",
      "url": "https://search.parallel.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start parallel-search and inspect its tools.

VS Code configuration

{
  "servers": {
    "parallel-search": {
      "type": "http",
      "url": "https://search.parallel.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.

Gemini CLI configuration

gemini mcp add --transport http parallel-search https://search.parallel.ai/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.

Claude Desktop configuration

{
  "mcpServers": {
    "parallel-search": {
      "url": "https://search.parallel.ai/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.

Windsurf configuration

{
  "mcpServers": {
    "parallel-search": {
      "serverUrl": "https://search.parallel.ai/mcp"
    }
  }
}

See all 782

Do you run Parallel Search?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing