Higress AI-Search MCP Server
@MCP-Mirror
About Higress AI-Search MCP Server
Mirror of
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Higress AI-Search MCP Server?
The Higress AI-Search MCP Server is a Model Context Protocol (MCP) server that provides an AI search tool. It enhances AI model responses with real‑time search results from multiple search engines through the Higress ai‑search feature. This server is for developers and users who want to give AI assistants access to live web, academic, and internal knowledge data.
How to use Higress AI-Search MCP Server?
Install via uvx (automatic from PyPI) or uv with a local clone. Configure the server by setting environment variables – MODEL (required) and optionally HIGRESS_URL (default http://localhost:8080/v1/chat/completions) and INTERNAL_KNOWLEDGE_BASES. Add the server configuration to your MCP client (e.g., Claude Desktop or Cline).
Key features of Higress AI-Search MCP Server
- Internet search via Google, Bing, and Quark
- Academic search via Arxiv
- Internal knowledge base search
- Real‑time search result integration into AI responses
- Configurable LLM model and Higress endpoint
Use cases of Higress AI-Search MCP Server
- Enhance chatbot answers with up‑to‑date web information
- Retrieve scientific papers and research from Arxiv
- Search internal company documents (employee handbook, policies)
FAQ from Higress AI-Search MCP Server
What search engines are supported?
Google, Bing, and Quark for internet search; Arxiv for academic search; plus configurable internal knowledge bases.
What environment variables are needed?
MODEL is required. HIGRESS_URL is optional (defaults to http://localhost:8080/v1/chat/completions). INTERNAL_KNOWLEDGE_BASES is optional for describing your internal knowledge sources.
How do I install the server?
You can use uvx to install automatically from PyPI, or clone the repository and run with uv pointing to the local source.
What are the prerequisites?
You need uv for package management and a Higress gateway configured with the ai‑search and ai‑proxy plugins.
Who should use this server?
Anyone who wants to give MCP‑compatible AI assistants (like those in Claude Desktop or Cline) the ability to perform live searches across the web, academic sources, or internal knowledge bases.
More Search MCP servers
Perplexity MCP Zerver
wysh3MCP web search using perplexity without any API KEYS
Google Search MCP Server
mixelpixxMCP Server built for use with Claude Code, Claude Desktop, VS Code, Cline - enable google search and ability to follow links and research websites
🚀 OneSearch MCP Server: Web Search & Crawl & Scraper & Extract
yokingma🚀 OneSearch MCP Server: Web Search & Scraper & Extract, Support agent-browser, SearXNG, Tavily, DuckDuckGo, Bing, etc.
DuckDuckGo Search MCP Server
nickclydeA Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
小红书自动搜索评论工具(MCP Server 2.0)
chenningling这是一款基于 Playwright 开发的小红书自动搜索和评论工具,作为 MCP Server,可通过特定配置接入 MCP Client(如Claude for Desktop),帮助用户自动完成登录小红书、搜索关键词、获取笔记内容及发布AI生成评论等操作。
Comments