About openGemini-mcp-server
openGemini-mcp-server is an MCP server for CNCF openGemini, giving AI assistants structured ways to inspect and query databases. It lists databases and measurements, reads sample data, and runs limited InfluxQL queries.
Key features
- 01List cluster databases
- 02View database measurements
- 03Read sample measurement data
- 04Run SELECT or SHOW queries
Use cases
- 01Inventory databases in an openGemini cluster
- 02Inspect measurements in a database
- 03Retrieve sample measurement data
- 04Query a cluster with InfluxQL
MCP support
The MCP server exposes tools for listing openGemini databases and measurements, reading sample data, and executing InfluxQL queries.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEopenGemini-mcp-server
A Model Context Protocol (MCP) server implementation for CNCF openGemini.
This server provides AI assistants with a secure and structured way to explore and analyze databases.
Capabilities
-
list_databases- List all databases on your openGemini cluster.
-
list_measurements- List all measurements in a database.
- Input:
database(string): The name of the database.
-
read_resource- Read sample data from a measurement.
- Input:
measurement(string): The name of the measurement.
-
execute_influxql- Execute an InfluxQL on your openGemini cluster.
- Input:
query(string): InfluxQL query to execute. - Only support query start with
SELECTorSHOW.
Installation
pip install .
Configuration
-
Open the Claude Desktop configuration file located at:
- On macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - On Windows:
%APPDATA%/Claude/claude_desktop_config.json
- On macOS:
-
Add the following:
{
"mcpServers": {
"mcp-openGemini": {
"command": "/path/to/python",
"args": [
"-m",
"mcp_openGemini.server"
],
"env": {
"OPENGEMINI_HOST": "<opengemini-host>",
"OPENGEMINI_PORT": "<opengemini-port>",
"OPENGEMINI_USER": "<opengemini-user>",
"OPENGEMINI_PASSWORD": "<opengemini-password>"
}
}
}
}
Update the environment variables to point to your own openGemini service.
- Restart Claude Desktop to apply the changes.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.