H

Hermes Search (Azure Cognitive Search)

Hermes Search MCP Server is an open - source service based on the Model Context Protocol, providing full - text and semantic search functions integrated with Azure Cognitive Search, and supporting multiple AI client tools.
2.5 points
15

What is Hermes Search MCP Server?

Hermes Search is an intelligent search server based on the Model Context Protocol (MCP), which enables AI systems (such as Claude, Cursor, etc.) to seamlessly connect to the Azure Cognitive Search service, achieving efficient document search and management functions.

How to use Hermes Search MCP Server?

Simply configure your AI client (Cline, Cursor, or Claude Desktop) and provide the credentials for the Azure search service to start using the powerful search function.

Use cases

Suitable for scenarios where AI assistants need to access enterprise knowledge bases, technical documents, or personal document collections, supporting fast retrieval of relevant information.

Main features

Full-text searchSupports full-text retrieval of structured/unstructured data
Semantic searchUnderstands search intent based on AI, not just keyword matching
Document managementSupports operations such as indexing, updating, and deleting documents
Multi-client compatibilityCompatible with multiple AI clients such as Cline, Cursor, and Claude Desktop

Advantages and limitations

Advantages
Ready to use, start with one - click via npx
Deeply integrated with Azure Cognitive Search
Supports multiple popular AI clients
Provides a type - safe TypeScript interface
Limitations
Requires an existing Azure Cognitive Search service
Currently mainly supports English content search
Advanced functions require certain configuration knowledge

How to use

Install the service
Run directly via npx or install using the Smithery tool
Configure the client
Configure accordingly based on the AI client you are using (Cline, Cursor, or Claude Desktop)
Provide Azure credentials
Set your Azure Cognitive Search service endpoint, API key, and index name in the configuration file
Restart the client
After completing the configuration, restart your AI client to load the search function

Usage examples

Technical document searchQuickly find relevant solutions in a large technical document library
Knowledge base expansionAdd new knowledge to the enterprise knowledge base
Research material retrievalFind relevant research in a collection of research papers

Frequently Asked Questions

Why doesn't my search return any results?
How do I know if the service is running normally?
Which file formats are supported for indexing?
What are the limitations of indexing a large number of documents?

Related resources

Azure Cognitive Search documentation
Microsoft's official documentation for the Azure search service
Model Context Protocol specification
Official specification of the MCP protocol
GitHub repository
Project source code and issue tracking
Installation
Copy the following command to your Client for configuration
{
  "mcpServers": {
    "hermes-search-mcp": {
      "command": "npx",
      "args": ["-y", "hermes-search-mcp@latest"],
      "env": {
        "AZURE_SEARCH_ENDPOINT": "your-search-endpoint",
        "AZURE_SEARCH_API_KEY": "your-api-key",
        "AZURE_SEARCH_INDEX_NAME": "your-index-name"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

{
  "mcpServers": {
    "hermes-search-mcp": {
      "command": "npx",
      "args": ["-y", "hermes-search-mcp@latest"],
      "env": {
        "AZURE_SEARCH_ENDPOINT": "your-search-endpoint",
        "AZURE_SEARCH_API_KEY": "your-api-key",
        "AZURE_SEARCH_INDEX_NAME": "your-index-name"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
337
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
824
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
222
4 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
202
4.3 points
M
Modelcontextprotocol
Certified
This project is an implementation of an MCP server integrated with the Sonar API, providing real-time web search capabilities for Claude. It includes guides on system architecture, tool configuration, Docker deployment, and multi-platform integration.
TypeScript
1.1K
5 points
B
Bilibili MCP Js
Certified
A Bilibili video search server based on the Model Context Protocol (MCP), providing API interfaces to support video content search, paginated queries, and video information return, including LangChain call examples and test scripts.
TypeScript
240
4.2 points
M
MCP Server Weread
The WeRead MCP Server is a lightweight service that bridges WeRead data and AI clients, enabling in - depth interaction between reading notes and AI.
TypeScript
372
4 points
M
MCP Obsidian
This project is an MCP server used to interact with the Obsidian note application through the Local REST API plugin of Obsidian. It provides various tools to operate and manage files in Obsidian, including listing files, retrieving file content, searching, modifying content, and deleting files.
Python
878
5 points
Featured MCP Services
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
131
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
824
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
80
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
555
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.6K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
279
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
746
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIbase