The Higress AI-Search MCP Server enhances AI model responses with real-time search results from various sources:
Internet Search: Retrieve information from Google, Bing, and Quark
Academic Search: Access scientific papers and research from Arxiv
Internal Knowledge Search: Query company policies, product documentation, and technical specifications
Provides academic search capabilities for scientific papers and research
Allows searching for general web information through Google search engine
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Higress AI-Search MCP Server search for recent advancements in quantum computing on Arxiv"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides an AI search tool to enhance AI model responses with real-time search results from various search engines through Higress ai-search feature.
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
Internet Search: Google, Bing, Quark - for general web information
Academic Search: Arxiv - for scientific papers and research
Internal Knowledge Search
The server can be configured using environment variables:
HIGRESS_URL(optional): URL for the Higress service (default: http://localhost:8080/v1/chat/completions).
MODEL(required): LLM model to use for generating responses.
INTERNAL_KNOWLEDGE_BASES(optional): Description of internal knowledge bases.
Using uvx will automatically install the package from PyPI, no need to clone the repository locally.
{
"mcpServers": {
"higress-ai-search-mcp-server": {
"command": "uvx",
"args": [
"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"
}
}
}
}Using uv requires cloning the repository locally and specifying the path to the source code.
{
"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"
}
}
}
}This project is licensed under the MIT License - see the LICENSE file for details.
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. Dates show when Glama detected each change.
v1.0.1ai_searchWith 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.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
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.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/cr7258/higress-ai-search-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
