Higress ai-search 기능을 통해 다양한 검색 엔진의 실시간 검색 결과로 AI 모델의 응답을 향상시키는 AI 검색 도구를 제공하는 MCP(Model Context Protocol) 서버입니다.
Related MCP server: OneSearch MCP Server
https://github.com/user-attachments/assets/60a06d99-a46c-40fc-b156-793e395542bb
https://github.com/user-attachments/assets/5c9e639f-c21c-4738-ad71-1a88cc0bcb46
인터넷 검색 : Google, Bing, Quark - 일반 웹 정보 검색
학술 검색 : Arxiv - 과학 논문 및 연구용
내부 지식 검색
서버는 환경 변수를 사용하여 구성할 수 있습니다.
HIGRESS_URL (선택 사항): Higress 서비스의 URL(기본값: http://localhost:8080/v1/chat/completions ).
MODEL (필수): 응답을 생성하는 데 사용할 LLM 모델입니다.
INTERNAL_KNOWLEDGE_BASES (선택 사항): 내부 지식 기반에 대한 설명입니다.
uvx를 사용하면 PyPI에서 패키지가 자동으로 설치되므로 로컬로 저장소를 복제할 필요가 없습니다.
지엑스피1
uv를 사용하려면 로컬로 저장소를 복제하고 소스 코드 경로를 지정해야 합니다.
{
"mcpServers": {
"higress-ai-search-mcp-server": {
"command": "uv",
"args": [
"--directory",
"path/to/src/higress-ai-search-mcp-server",
"run",
"higress-ai-search-mcp-server"
],
"env": {
"HIGRESS_URL": "http://localhost:8080/v1/chat/completions",
"MODEL": "qwen-turbo",
"INTERNAL_KNOWLEDGE_BASES": "Employee handbook, company policies, internal process documents"
}
}
}
}이 프로젝트는 MIT 라이선스에 따라 라이선스가 부여되었습니다. 자세한 내용은 라이선스 파일을 참조하세요.
Enhance AI model responses with real-time search results from search engines.
This tool sends a query to Higress, which integrates with various search engines to provide up-to-date information:
🌐 Internet Search: Google, Bing, Quark - for general web information 📖 Academic Search: Arxiv - for scientific papers and research 👨💻 Internal Knowledge Search: Company documentation, product manuals, FAQ database, and technical specifications stored in our internal systems
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The user's question or search query |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool sends queries to Higress and integrates multiple engines, but does not mention behavior traits such as authentication needs, rate limits, failure modes, or how results are processed. This is minimal disclosure for a tool that performs external queries.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with a lead sentence and a bullet list with emojis. It presents information efficiently, though the phrase 'provide up-to-date information' is slightly redundant with 'real-time search results'. Overall well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given one parameter and an output schema, the description explains sources and purpose adequately. However, it lacks details on how results are returned (e.g., format, ranking) and whether search scope can be controlled. It is minimally complete for a search tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, providing baseline 3. The description adds value by explaining that the query is used to search multiple sources (Internet, Academic, Internal) and gives examples. This adds context beyond the bare schema description, justifying a 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool enhances AI responses with real-time search results from search engines via Higress. It identifies the verb 'enhance' and the resource 'search results', making the purpose clear. However, the primary functional verb could be more direct like 'search'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when up-to-date information is needed (e.g., 'real-time search results'). It lists categories of search sources, but does not provide explicit when-to-use, when-not-to-use, or alternatives. Since there are no sibling tools, the lack of exclusions is less critical.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.1ai_searchScored across 1 tool
With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined as a unified search interface.
Only one tool exists, so naming consistency is trivially met. The name 'ai_search' is descriptive and follows a reasonable pattern.
A single search tool is slightly under the typical 3-15 range, but it consolidates multiple search capabilities (internet, academic, internal) into one unified interface, which can be reasonable for a focused server.
The tool covers key search domains (internet, academic, internal knowledge), but lacks explicit support for advanced features like filters, pagination, or custom sources, which may be needed for complex queries.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A Model Context Protocol server for Wix AI tools
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
