MCP.so
登录
P

Parallel Search MCP Server

@parallel-web

基本信息

传输方式

stdio

认证方式

无需认证

分类

搜索

作者

parallel-web

提交者

George Pickett

关于 Parallel Search MCP Server

Free web search and page fetching for AI agents. No account or API key required. Free-tier rate limits apply.

#parallel-search#web-search#mcp

连接信息

https://search.parallel.ai/mcp

接入方式

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

Parallel Search MCP Server 工具

2

Purpose: Perform web searches and return LLM-friendly results, including excerpts that are usually sufficient to answer directly without a follow-up fetch. Ideal Use Cases: - Answering questions that require fresh or current information - Research, comparison, documentation, and troubleshooting questions - Broad tasks where multiple `search_queries` can be issued in a single call For multiple independent objectives, make one web_search call per objective concurrently. Put related query variations for the same objective in a single call's search_queries list.

Purpose: Fetch and extract relevant content from specific web URLs. Use only when web_search excerpts are insufficient for the task at hand. Ideal Use Cases: - The user asked about a specific URL or page - You need exact wording or quotes that excerpts may have truncated - You need full-page analysis (long article, document, or page structure) - web_search excerpts are conflicting or clearly insufficient to answer For multiple independent extraction objectives, make separate web_fetch calls concurrently. Put related URLs that share one objective in a single call.

概览

What is Parallel Search MCP?

Free web search and page fetching for AI agents. The hosted Search MCP works without an account or API key. Free-tier rate limits apply.

Setup

Connect to https://search.parallel.ai/mcp using Streamable HTTP. No authentication or local server is required.

See the official setup documentation for client-specific instructions.

Tools

  • web_search: Search the web and return relevant results with excerpts.
  • web_fetch: Fetch web pages and extract relevant content.

Is it free?

Yes. The endpoint above supports anonymous free access without an account or API key, subject to free-tier rate limits.

Which clients can connect?

Any MCP client that supports Streamable HTTP, including Claude Code, Cursor, VS Code, and Codex.

This listing covers the free Search MCP. Paid Task MCP, authenticated Search options, and the Parallel CLI are separate offerings.

常见问题

1

Parallel Search 远程 MCP 服务器是什么?

Parallel Search 的远程 MCP 服务器是一个托管的 Model Context Protocol 端点,地址是 https://search.parallel.ai/mcp,AI 助手无需在本地安装或运行任何东西即可连接。

2

怎么连接 Parallel Search 的 MCP 服务器?

把端点 https://search.parallel.ai/mcp 添加到任意支持 MCP 的客户端,比如 Claude Code、Cursor 或 VS Code。本页的接入代码块可以一步配置好每个客户端。

3

Parallel Search 的 MCP 服务器需要认证吗?

不需要。Parallel Search 的 MCP 服务器不需要认证——直接用端点地址连接即可。

4

Parallel Search 的 MCP 服务器用的是哪种传输方式?

Parallel Search 暴露的是 stdio 端点,这是远程 MCP 服务器普遍使用、主流客户端都支持的传输方式。

评论