search-server
基于MCP的搜索服务器，支持多引擎检索. search-server is a Model Context Protocol (MCP) server maintained by fengin. It connects to MCP-compatible clients such as Claude Desktop, Cursor, Cline, and other agents that speak the protocol. It exposes 5 tools, including Brave Search, Brave Location Search, Metaso Search, Metaso Scholar Search and Bocha Search, that an agent can call directly. It is categorized under Tool/Search and AI/Integration.
什么是MCP
这是用于搜索功能的模型上下文协议（MCP）实现，可为Claude Desktop和Cursor等AI工具提供与多个搜索引擎（Brave、Metaso、Bocha）的集成。
如何使用这个MCP
在server.py中配置所需的搜索引擎，为选定的引擎设置API密钥，然后通过兼容AI工具的MCP服务器设置进行集成。
这个MCP的用途
增强AI工具的实时网络/搜索能力，使其能够直接从多个搜索提供商获取最新信息并整合到工作流程中。
AIMCP authority
DR and traffic signal for the AIMCP public domain.
Frequently asked questions
What is the search-server MCP server?
search-server is a Model Context Protocol server from fengin. It lets MCP-compatible AI clients call its tools over a standard interface, so agents like Claude, Cursor, and Cline can use it without custom integration.
How do I connect search-server to my AI client?
Add search-server to your client's MCP configuration using the stdio or SSE connection shown in the usage examples on this page, then restart the client to load the server.
What tools does search-server provide?
search-server provides 5 tools: Brave Search, Brave Location Search, Metaso Search, Metaso Scholar Search and Bocha Search.
Is search-server free to use?
search-server is listed on AIMCP for free. Any API keys or accounts required by the underlying service are set by its provider.
Vernclaw Plugins for OpenClaw
Ready-to-use connectors for SEO data, social reading & content generation. Pay-as-you-go credits with audit logs.