mcp-server-openmetadata
by tpavelek
This project implements a Model Context Protocol (MCP) server for OpenMetadata, enabling seamless integration with MCP clients. It provides a standardized way to interact with OpenMetadata through the Model Context Protocol.
Last updated: N/A
What is mcp-server-openmetadata?
This is a Model Context Protocol (MCP) server implementation for OpenMetadata. It wraps OpenMetadata's REST API, allowing MCP clients to interact with OpenMetadata in a standardized way.
How to use mcp-server-openmetadata?
To use this server, you need to set up the environment variables for authentication (either Token Authentication or Basic Authentication) and configure it with a MCP client like Claude Desktop. Configuration examples are provided in the README. You can also run the server manually using python src/server.py.
Key features of mcp-server-openmetadata
Standardized interaction with OpenMetadata
Wraps OpenMetadata's REST API
Supports Token and Basic Authentication
Integration with MCP clients
Use cases of mcp-server-openmetadata
Integrating OpenMetadata with MCP-compatible tools
Providing a consistent interface for interacting with OpenMetadata's data assets
Automating data governance workflows using MCP
Building custom applications that leverage OpenMetadata's metadata
FAQ from mcp-server-openmetadata
What is MCP?
What is MCP?
MCP stands for Model Context Protocol, a standardized way for clients to interact with metadata servers.
What authentication methods are supported?
What authentication methods are supported?
The server supports both Token Authentication (recommended) and Basic Authentication.
How do I configure the server with Claude Desktop?
How do I configure the server with Claude Desktop?
You can configure the server by adding it to your claude_desktop_config.json file, providing the command, arguments, and environment variables for authentication.
How can I run the server manually?
How can I run the server manually?
You can run the server manually using the command python src/server.py, with optional --port and --transport arguments.
What data assets are supported?
What data assets are supported?
Currently, the server supports listing, getting, creating, updating, and deleting tables. Other data assets have limited or no support.