Watson Discovery
A server based on the Model Context Protocol (MCP) for securely interacting with Watson Discovery and supporting query operations through natural language processing.
rating : 2 points
downloads : 7.9K
What is the Watson Discovery MCP Server?
The Watson Discovery MCP Server is a secure and efficient tool for connecting AI assistants with IBM Watson Discovery. It allows users to list projects, query collections, and perform complex searches through natural language processing.How to use the Watson Discovery MCP Server?
First, set the environment variables and install the necessary dependencies, then start the server. You can integrate this server directly into a desktop application or run it separately.Applicable Scenarios
Suitable for enterprise scenarios that require rapid retrieval of large amounts of documents, such as the legal, financial, and medical industries.Main Features
List Available Projects
Easily view all your projects in Watson Discovery.
List Collections in a Project
Browse the specific content collections of each project.
Natural Language Processing Query
Quickly obtain the required information through simple natural language input.
Advantages
Powerful natural language processing capabilities
Support for multi - platform integration
High - security guarantee
Limitations
Requires proper API key configuration
Has certain requirements for the network environment
How to Use
Install Dependencies
Ensure that Python and the uv tool are installed. Run `uv install` to install the necessary dependencies.
Start the Server
Run the following command to start the MCP server: `uv run main-py`.
Usage Examples
List All Projects
Use the MCP server to list all available Watson Discovery projects.
Perform a Natural Language Query
Perform complex query tasks through natural language input.
Frequently Asked Questions
How to set the environment variables?
Does the server support multiple languages?
Related Resources
Official Documentation
Detailed API documentation and usage guides.
GitHub Repository
Source code and contribution guides.

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
15.1K
4.5 points

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
17.2K
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
47.7K
4.3 points

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
25.5K
5 points

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#
19.8K
5 points

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
46.8K
4.5 points

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
15.4K
4.5 points

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
30.8K
4.8 points





