Parallel Search MCP
Free web search for your coding agent. Find current documentation, check facts, and read web pages without leaving your agent. No account or API key needed to get started. It is available as a remote MCP endpoint.
Teams that work with coding agents, content extraction and web search and want a hosted endpoint instead of running a local process.
VERIFIED ACTIVE
LAST COMMIT 2026-09-25 · ★ 20 · #70 OF 97 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-30
MIT · how we verify → /methodology
01 · Install Parallel Search MCP
before you install - you'll need
The README does not document required environment variables for a basic install.
Claude Code
claude mcp add parallel-web-search-mcp --transport http https://search-mcp.parallel.ai/mcp Claude Desktop / Cursor / VS Code - add to config
{
"mcpServers": {
"parallel-web-search-mcp": {
"url": "https://search-mcp.parallel.ai/mcp"
}
}
} Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.
Using another client? Same JSON, different key
Claude Desktop · mcpServers
Cursor · mcpServers
VS Code · servers
Windsurf · mcpServers
Zed · context_servers
Cline · mcpServers
Roo Code · mcpServers
Continue · mcpServers
LibreChat · mcpServers
Gemini CLI · mcpServers
Codex CLI · mcp_servers
Full setup guides: every client.
02 · Evidence
https://search-mcp.parallel.ai/mcp
transport: streamable-http
endpoint alive - authentication required · probed 2026-09-30
Security posture
What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.
runs as remote - your agent's requests go to search-mcp.parallel.ai
endpoint auth requires authentication - rejected our unauthenticated MCP initialize
repo age created 2026-09-03 - young repo, little track record yet
license MIT - declared in the repository
registry vendor namespace ai.parallel - domain-verified with the official MCP registry
03 · What Parallel Search MCP can do
Prose above is summarized from the project's README and registry record - no invented capabilities.
Latest releases
v0.1.1 · 2026-09-21
Tightens the Hermes setup guidance: · Makes clear that the catalog submission is still awaiting approval. · Points authenticated users to the supported options, including Hermes’s native paid provider. · Refers to the…
v0.1.0 · 2026-09-21
Adds optional Hermes Agent packaging for Parallel’s free hosted Search MCP. · Installable through portable Agent Plugins v1, with anonymous web_search and web_fetch tools and the existing setup skill. Existing Claude…
04 · Who maintains Parallel Search MCP
Parallel Search MCP is maintained by parallel-web. We track 2 MCP servers from parallel-web - 2 actively maintained, 36 combined GitHub stars, oldest repo from Oct 2025. Full record: all servers from parallel-web.
05 · Facts
- repository
- github.com/parallel-web/search-mcp
- website
- https://parallel.ai/
- category
- web scraping - ranked #70 of 97 actively-maintained web scraping servers as of 2026-09-30.
- release cadence
- 2 releases in the last 90 days (latest 2026-09-21)
- registry
- ai.parallel/search-mcp (active, first published 2026-01-09)
06 · Parallel Search MCP FAQ
What is Parallel Search MCP?
Free web search for your coding agent. Find current documentation, check facts, and read web pages without leaving your agent. No account or API key needed to get started. It is available as a remote MCP endpoint.
Is Parallel Search MCP still maintained?
Yes - as of 2026-09-30, its last commit was 2026-09-25 and it shipped 2 releases in the last 90 days. We re-verify nightly.
How do I install Parallel Search MCP?
Run `claude mcp add parallel-web-search-mcp --transport http https://search-mcp.parallel.ai/mcp`. The README does not document required environment variables for a basic install. You can also paste the ready-made client config above.
Does Parallel Search MCP require authentication?
Yes - when we probed the endpoint on 2026-09-30, it rejected an unauthenticated MCP initialize; you'll need credentials to connect.
07 · Alternatives to Parallel Search MCP
Alternatives to Parallel Search MCP
Maintained web scraping servers if Parallel Search MCP isn't the fit.
- Apify MCP Server Extract data from any website with thousands of scrapers, crawlers, and automations on Apify Store ⚡ ★ 8,922 · 2026-09-29
- Firecrawl MCP Server MCP server for Firecrawl - web search, scraping, and biomedical/arXiv paper search. ★ 7,536 · 2026-09-30
- Exa Connect AI agents to Exa for web search, content fetching, and multi-step research. ★ 5,058 · 2026-09-23
- Tavily MCP MCP server for advanced web search using Tavily ★ 2,416 · 2026-09-29
- CRW Web Scraper Open-source web scraper for AI agents with scrape, crawl, and map tools ★ 1,088 · 2026-09-30
- Open Brand Extract brand assets (logos, colors, backdrop images, brand name) from any website URL ★ 799 · 2026-05-12
Pairs well with
Servers that cover what Parallel Search MCP doesn't - only shown when the pairing reason fits the companion.
- SearXNG Search → search companion search · ★ 1,268
- Server Search → search companion search · ★ 39,168
- Supabase → database companion database · ★ 2,926
- MongoDB MCP Server → database companion database · ★ 1,137
- Codebase Memory → memory companion memory · ★ 45,519
- Memorix → memory companion memory · ★ 819
More web scraping MCP servers · Parseur · Multi Scraper MCP · Pinkpixel Dev Web Scout MCP · Fetch V2 · Crawlgraph MCP