mcflux
Provides tools to query and explore time-series data in an InfluxDB v1 instance, including listing databases, measurements, tag keys, field keys, tag values, and executing read-only InfluxQL queries.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcfluxlist databases"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcflux
Read-only MCP server for InfluxDB v1. Lets Claude (Desktop or Code) query and explore your time-series data through the Model Context Protocol.
Tools
Tool | Description |
| Check connectivity and return the InfluxDB version |
| List all databases |
| List measurements in a database |
| List tag keys, optionally filtered by measurement |
| List field keys and their types |
| List values for a specific tag key |
| Execute a read-only InfluxQL query (SELECT/SHOW only) |
Write operations (CREATE, DROP, DELETE, INSERT, etc.) are blocked at the server level.
Related MCP server: InfluxDB MCP Server
Requirements
Python 3.10+
uv package manager
An InfluxDB v1 instance
Installation
Claude Desktop (extension)
Download the latest .mcpb from Releases, then:
Open Claude Desktop
Go to Settings > Extensions > Advanced settings
Click Install Extension and select the
.mcpbfileFill in your InfluxDB URL, username, and password in the configuration form
Claude Desktop (manual)
Add to claude_desktop_config.json:
Windows:
%AppData%\Claude\claude_desktop_config.jsonmacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"influxdb": {
"command": "uv",
"args": ["--directory", "/path/to/mcflux", "run", "server.py"],
"env": {
"INFLUXDB_URL": "http://localhost:8086",
"INFLUXDB_USERNAME": "myuser",
"INFLUXDB_PASSWORD": "mypass"
}
}
}
}Claude Code
Add to .claude/settings.json or your project settings:
{
"mcpServers": {
"influxdb": {
"command": "uv",
"args": ["--directory", "/path/to/mcflux", "run", "server.py"],
"env": {
"INFLUXDB_URL": "http://localhost:8086",
"INFLUXDB_USERNAME": "myuser",
"INFLUXDB_PASSWORD": "mypass"
}
}
}
}Configuration
Environment variable | Required | Default | Description |
| No |
| InfluxDB HTTP API URL |
| No | (none) | Username for basic auth |
| No | (none) | Password for basic auth |
Omit INFLUXDB_USERNAME and INFLUXDB_PASSWORD if your instance does not require authentication.
Building the .mcpb bundle
npm install -g @anthropic-ai/mcpb
mcpb pack .This produces a mcflux.mcpb file that can be installed as a Claude Desktop extension.
License
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/dmayan-ss/mcp-influx1'
If you have feedback or need assistance with the MCP directory API, please join our Discord server