Skip to main content

Kubernetes assistant powered by Model Context Protocol (MCP)

Project description

K8s MCP

A Kubernetes assistant powered by Model Context Protocol (MCP) and Google Gemini.

Requirements

  • Python 3.10+
  • Kubernetes cluster with kubeconfig configured
  • Node.js 18+ (for frontend)
  • Bun (optional, for faster frontend builds)

Quick Start

Use the Makefile to run different components:

1. MCP Server

Starts the MCP server that communicates with your Kubernetes cluster.

make mcp-server

Requires: Active Kubernetes cluster and configured kubeconfig.

2. CLI Mode

Interactive command-line interface to query your Kubernetes cluster.

make cli

3. Web Application (Backend + Frontend)

Start the backend API server:

make backend

Start the frontend in another terminal:

make frontend

Then open http://localhost:5173 in your browser.

4. All at Once

Start all services in background (development mode):

make dev

Project Structure

k8s_mcp_server.py    - MCP server implementation
mcp_client.py        - CLI client
app/
  backend/           - FastAPI server
  frontend/          - React UI

Configuration

Ensure your kubeconfig is at ~/.kube/config or set the KUBECONFIG environment variable.

The MCP server exposes 32 Kubernetes tools for managing resources, deployments, services, and more.

Features

  • Real-time Kubernetes operations via MCP tools
  • Chat interface with tool call results
  • Inline tool call display in messages
  • WebSocket streaming for live responses
  • Automatic WebSocket reconnection

Make Commands

Available make targets (run make <target>):

  • make help — Show all available commands
  • make mcp-server — Start the K8s MCP server
  • make cli — Launch the interactive CLI client
  • make backend — Start the FastAPI backend
  • make frontend — Start the React frontend
  • make dev — Start backend and frontend in the background (development mode)
  • make logs — Tail service logs
  • make stop — Stop all background services
  • make install-deps — Install project dependencies
  • make clean — Remove build artifacts and cache files

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

iflow_mcp_rahul007_bit_mcp_k8s-0.1.0.tar.gz (12.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file iflow_mcp_rahul007_bit_mcp_k8s-0.1.0.tar.gz.

File metadata

  • Download URL: iflow_mcp_rahul007_bit_mcp_k8s-0.1.0.tar.gz
  • Upload date:
  • Size: 12.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_rahul007_bit_mcp_k8s-0.1.0.tar.gz
Algorithm Hash digest
SHA256 761bfb4e192b55962389c08c96ee1a1218ec6d7594b8e9e5566f0a0add26bbff
MD5 081a1dcf24cb3ec055e5b8bac075cdc6
BLAKE2b-256 f392d35425d04df01cc1911c4fa4f8a7657578bb4cb9d05561955319d77ae9ba

See more details on using hashes here.

File details

Details for the file iflow_mcp_rahul007_bit_mcp_k8s-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: iflow_mcp_rahul007_bit_mcp_k8s-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 15.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_rahul007_bit_mcp_k8s-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 40cfa048edadb4074a855553f0aa970f30803512cc1a35450ff166935f9920f5
MD5 129183b9e7ca84e80e03753d20133407
BLAKE2b-256 c7b1132848c39c99a8e583b94d611ace0da7daf886c0a69354c15d186f91bd6a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page