ibm-watsonx-gov-catalog-mcp-server
Bridges AI agents with tools on IBM watsonx governed agentic catalog, enabling secure governance and tool invocation via the Model Context Protocol.
README
ibm-watsonx-gov-catalog-mcp-server
The ibm-watsonx-gov-catalog-mcp-server is a Model Context Protocol (MCP)-compliant server that seamlessly connects AI agents with tools hosted on watsonx governed agentic catalog.
Overview
- Protocol: Model Context Protocol (MCP)
- Purpose: Acts as a bridge between agentic AI frameworks and tools on governance catalog
- Supported Environments: Watsonx SaaS (Envs Supported : Sydney , Toronto)
- Agent Compatibility: The agentic framework must support the MCP standard (via Stdio).
Note: This server will not function with agents that do not support MCP.
Prerequisites
- Python version 3.11 or later
- Access to your SaaS environment
- Ensure your Agent framework supports MCP protocol
Setup
Step 1: Install Python
- Official Installer: https://www.python.org/downloads/
Step 2: Create a virtual environment
python -m venv .venv
Running the Server
uv run ibm-watsonx-gov-catalog-mcp-server
Step 3: Activate the virtual environment
source .venv/bin/activate # macOS/Linux
.venv\Scripts\activate # Windows
Step 4: Install the uv package manager
pip install uv
uvpackage: https://pypi.org/project/uv/
Build the wheel file
uv pip install build
uv run python -m build
Build and Run the server
uv run ibm-watsonx-gov-catalog-mcp-server
Testing using MCP Inspector
Set the following environment variables
For Watsonx SaaS
If you have not already, provision an instance of IBM WatsonX Governance instance using the link in the Cloud catalog .
export WATSONX_APIKEY=<API KEY>
export WATSONX_REGION=<WATSONX_REGION>
NOTE:
-
For WATSONX_APIKEY: This is required for IBM watsonx.governance capabilities. Your Cloud API key can be generated by going to the Users section of the Cloud console. From that page, click your name, scroll down to the API Keys section, and click Create an IBM Cloud API key. Give your key a name and click Create, then copy the created key and paste it below.
-
For WATSONX_REGION: Set if you are using IBM watsonx.governance as a service in a regional data center other than default Dallas (us-south), in Texas US. Supported region values are "us-south", "eu-de", "au-syd", "ca-tor", "jp-tok".
Invoke MCP inspector
npx @modelcontextprotocol/inspector uv run ibm-watsonx-gov-catalog-mcp-server -e WATSONX_APIKEY=<WASONX_APIKEY> -e WATSONX_REGION=<WATSONX_REGION>
Limitations
- Environment credentials cannot be changed during runtime.
- To change credentials, either:
- Start a new server with new env variables
- To change credentials, either:
- Transport types supported :
stdio - Tool call is supported : OOTB tools , Tools created using custom code.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。