What is Influx Mcp

influx_mcp is a Model Context Protocol (MCP) server designed to provide secure, read-only access to InfluxDB 1.8 using JWT authentication. It allows AI assistants to query time-series data through a standardized interface.

Use cases

Use cases for influx_mcp include querying real-time data from sensors, monitoring application performance metrics, and analyzing historical data trends in various industries.

How to use

To use influx_mcp, first clone the repository and set up a .env file with your InfluxDB credentials. Then, build and run the Docker container. Authenticate using a JWT token and use various tools to query your InfluxDB data.

Key features

Key features of influx_mcp include secure JWT authentication, read-only access to InfluxDB, standardized querying interface, and support for Docker deployment.

Where to use

influx_mcp can be used in various fields that require time-series data analysis, such as IoT applications, monitoring systems, and data analytics platforms.

InfluxDB MCP Server

A Model Context Protocol (MCP) server that provides secure, read-only access to InfluxDB 1.8 via JWT authentication.

Overview

InfluxDB MCP Server allows AI assistants to query time-series data stored in InfluxDB through a standardized interface. It provides read-only access to your InfluxDB instance with authentication via JWT tokens.

Prerequisites

• Docker
• InfluxDB 1.8 instance (already running)
• Credentials for your InfluxDB instance

Installation

1. Clone the repository:

   git clone https://github.com/m4tyn0/influx_mcp
   cd influxdb-mcp-server
   

2. Create a .env file with your configuration :

   cp env.example .env
   

   INFLUXDB_HOST=
   INFLUXDB_PORT=8086
   INFLUXDB_USERNAME=
   INFLUXDB_PASSWORD=
   INFLUXDB_SSL=false
   INFLUXDB_VERIFY_SSL=true
   INFLUXDB_TIMEOUT=10
   JWT_SECRET=
   JWT_ALGORITHM=HS256
   

3. Build and run the Docker container:

   docker build -t influxdb-mcp-server .
   docker run -d --env-file .env -p 8000:8000 influxdb-mcp-server
   

JWT Authentication

The server uses JWT tokens for authentication. You need to generate a token to authenticate with the MCP server, here is a simple script to do that:

import jwt
import datetime

# Create a token
payload = {
    "sub": "username",  # Replace with the username you want to identify with
    "iat": datetime.datetime.utcnow(),
    "exp": datetime.datetime.utcnow() + datetime.timedelta(hours=1)
}
token = jwt.encode(payload, "your-jwt-secret", algorithm="HS256")
print(token)

Save this token for use with your MCP client.

Using with MCP Clients

1. Authenticate with the MCP server using the JWT token:

   Tool: auth
   Arguments: {"token": "your.jwt.token.here"}
   

2. Query your InfluxDB data:

   Tool: list_databases
   Arguments: {}
   

   Tool: list_measurements
   Arguments: {"database": "your_database_name"}
   

   Tool: query
   Arguments: {
     "database": "your_database_name",
     "query": "SELECT * FROM measurement_name LIMIT 10"
   }
   

Troubleshooting

If you encounter issues:

1. Connection errors to InfluxDB:

   • Verify the INFLUXDB_HOST is correct and accessible from the Docker container
   • Check that your InfluxDB credentials are correct
   • Ensure your InfluxDB instance is configured to accept connections from external hosts

2. Authentication issues:

   • Verify your JWT_SECRET is set correctly
   • Ensure the token you’re using matches the JWT_SECRET and hasn’t expired
   • Check that your InfluxDB credentials have read access to the databases

3. Check logs:

   docker logs 
   

Security Notes

• The MCP server only allows read-only access to your InfluxDB instance
• All queries are validated to ensure they begin with SELECT
• JWT authentication protects access to the MCP server
• Consider running the server in a private network for additional security

Thank you for working with me. If you have any issues with the code, or want more things built, hit me up: [email protected]