Lumino MCP Server

LUMINO MCP Server

[License] [Python] [MCP] [PyPI]

An open source MCP (Model Context Protocol) server empowering SREs with intelligent observability, predictive analytics, and AI-driven automation across Kubernetes, OpenShift, and Tekton environments.

Table of Contents

• Overview
• Features
• Quick Start
• Team Onboarding Guide
• Prerequisites
• Installation
• Usage Examples
• Configuration
• ML Model Persistence
• KubeArchive Integration
• Prometheus/Thanos Integration
• Available Tools
• Architecture
• How It Works
• MCP Client Integration
• Performance Considerations
• Troubleshooting
• Dependencies
• Contributing
• Security
• License
• Acknowledgments

Team Onboarding Guide

New to the SPRE MCP diagnostics stack (Lumino, PagerDuty, Slack, DevLake, ngit-memory, GitHub, GitLab, Konflux Portal, Sumo Logic, Jira)? Start here:

• docs/ONBOARDING_GUIDE.md — setup, first diagnostic, troubleshooting, three worked examples, and expected tool outputs

Overview

LUMINO MCP Server transforms how Site Reliability Engineers (SREs) and DevOps teams interact with Kubernetes clusters. By exposing 39 specialized tools through the Model Context Protocol, it enables AI assistants to:

• Monitor cluster health, resources, and pipeline status in real-time
• Analyze logs, events, and anomalies using statistical and ML techniques
• Troubleshoot failed pipelines with automated root cause analysis
• Predict resource bottlenecks and potential issues before they occur
• Simulate configuration changes to assess impact before deployment

Features

Kubernetes & OpenShift Operations

• Namespace and pod management
• Resource querying with flexible output formats
• Label-based resource search across clusters
• OpenShift operator and MachineConfigPool status
• etcd log analysis

Tekton Pipeline Intelligence

• Pipeline and task run monitoring across namespaces
• Detailed log retrieval with optional cleaning
• Failed pipeline root cause analysis
• Cross-cluster pipeline tracing
• CI/CD performance baselining

Advanced Log Analysis

• Smart log summarization with configurable detail levels
• Streaming analysis for large log volumes
• Hybrid analysis combining multiple strategies
• Semantic search using NLP techniques
• Anomaly detection with severity classification

Predictive & Proactive Monitoring

• Statistical anomaly detection using z-score analysis
• Predictive log analysis for early warning
• Resource bottleneck forecasting
• Certificate health monitoring with expiry alerts
• TLS certificate issue investigation

Event Intelligence

• Smart event retrieval with multiple strategies
• Progressive event analysis (overview to deep-dive)
• Advanced analytics with ML pattern detection
• Log-event correlation

Simulation & What-If Analysis

• Monte Carlo simulation for configuration changes
• Impact analysis before deployment
• Risk assessment with configurable tolerance
• Affected component identification

Quick Start

Get started with LUMINO in under 2 minutes:

For Claude Code CLI Users (Easiest)

Simply ask Claude Code to provision the Lumino MCP server for you by pasting this prompt:

Provision the Lumino MCP server as a project-local MCP integration:
1. Clone the repository:   git clone https://github.com/spre-sre/lumino-mcp-server.git
2. Install Python dependencies using uv:   cd lumino-mcp-server && uv sync
3. Create .mcp.json in the current project root (NOT inside lumino-mcp-server) with this configuration.   IMPORTANT: Replace <ABSOLUTE_PATH_TO_LUMINO> with the actual absolute path to the cloned lumino-mcp-server directory:
   {     "mcpServers": {       "lumino": {         "type": "stdio",         "command": "<ABSOLUTE_PATH_TO_LUMINO>/.venv/bin/python",         "args": ["<ABSOLUTE_PATH_TO_LUMINO>/main.py"],         "env": {           "PYTHONUNBUFFERED": "1"         }       }     }   }
4. After creating .mcp.json, inform the user to:   - Exit Claude Code completely   - Connect to their Kubernetes or OpenShift cluster (kubectl/oc login)   - Restart Claude Code in this project directory   - They will see a prompt to approve the Lumino MCP server   - Once approved, Lumino tools will be available (check with /mcp command)

For Other MCP Clients

Choose your preferred installation method:

• MCPM (Recommended): mcpm install @spre-sre/lumino-mcp-server
• Manual Setup: See detailed MCP Client Integration instructions

Verify Installation

Once installed, test with a simple query:

"List all namespaces in my Kubernetes cluster"

Prerequisites

Required

• Python 3.10 or higher - Core runtime
• MCP Client - One of:
  • Claude Desktop
  • Claude Code CLI
  • Gemini CLI
  • Cursor IDE

For Kubernetes Features

• Kubernetes/OpenShift Access - Valid kubeconfig with read permissions
• RBAC Permissions - Ability to list pods, namespaces, and other resources

Optional (Recommended)

• uv - Faster dependency management than pip
• MCPM - Easiest installation experience
• Prometheus - For advanced metrics and forecasting features

Installation

Using uv (recommended)

# Clone the repositorygit clone https://github.com/spre-sre/lumino-mcp-server.gitcd lumino-mcp-server
# Install dependenciesuv sync
# Run the serveruv run python main.py

Using pip

# Clone the repositorygit clone https://github.com/spre-sre/lumino-mcp-server.gitcd lumino-mcp-server
# Create virtual environmentpython -m venv venvsource venv/bin/activate  # On Windows: venv\Scripts\activate
# Install dependenciespip install -e .
# Run the serverpython main.py

Usage

Local Mode (stdio transport)

By default, the server runs in local mode using stdio transport, suitable for direct integration with MCP clients:

python main.py

Kubernetes Mode (HTTP streaming transport)

When running inside Kubernetes, set the namespace environment variable to enable HTTP streaming:

export KUBERNETES_NAMESPACE=my-namespacepython main.py

The server automatically detects the environment and switches transport modes.

Usage Examples

🔍 Intelligent Root Cause Analysis

Investigate and diagnose complex failures with automated analysis:

"Generate a comprehensive RCA report for the failed pipeline run 'build-api-pr-456' in namespace ci-cd"

"Analyze what caused pod crashes in namespace production over the last 6 hours and correlate with resource events"

"Investigate the TLS certificate issues affecting services in namespace ingress-nginx"

🎯 Predictive Intelligence & Forecasting

Anticipate problems before they impact your systems:

"Predict resource bottlenecks across all production namespaces for the next 48 hours"

"Analyze historical pipeline performance and detect anomalies in build times for the last 30 days"

"Check cluster certificate health and alert me about any certificates expiring in the next 60 days"

"Use predictive log analysis to identify potential failures in namespace monitoring before they occur"

🧪 Simulation & What-If Analysis

Test changes safely before applying them to production:

"Simulate the impact of increasing memory limits to 4Gi for all pods in namespace backend-services"

"Run a what-if scenario for scaling deployments to 10 replicas and analyze resource consumption"

"Simulate configuration changes for nginx ingress controller and assess risk to existing traffic"

🗺️ Topology & Dependency Mapping

Understand system architecture and component relationships:

"Generate a live topology map of all services, deployments, and their dependencies in namespace microservices"

"Map the complete dependency graph for the payment-service including all connected resources"

"Show me the topology of components affected by the cert-manager service"

🔬 Advanced Investigation & Forensics

Deep-dive into complex issues with multi-faceted analysis:

"Perform an adaptive namespace investigation for production - analyze logs, events, and resource patterns"

"Create a detailed investigation report for resource constraints and bottlenecks in namespace data-processing"

"Trace pipeline execution for commit SHA abc123def from source to deployment across all namespaces"

"Search logs semantically for 'authentication failures related to expired tokens' across the last 24 hours"

📊 CI/CD Pipeline Intelligence

Optimize and troubleshoot your continuous delivery pipelines:

"Establish performance baselines for all Tekton pipelines and flag runs deviating by more than 2 standard deviations"

"Trace the complete pipeline flow for image 'api:v2.5.3' from build to production deployment"

"Analyze failed pipeline runs in namespace tekton-pipelines and identify common failure patterns"

"Compare current pipeline run times against 30-day baseline and highlight performance degradation"

🎨 Progressive Event Analysis

Multi-level event investigation from overview to deep-dive:

"Start with an overview of events in namespace kube-system, then drill down into critical issues"

"Perform advanced event analytics with ML pattern detection for namespace monitoring over the last 12 hours"

"Correlate events with pod logs to identify the root cause of CrashLoopBackOff in namespace applications"

🚀 Real-Time Monitoring & Alerts

Stay informed about cluster health and pipeline status:

"Show me the status of all Tekton pipeline runs cluster-wide and highlight long-running pipelines"

"List all failed TaskRuns in the last hour with error details and recommended actions"

"Monitor OpenShift cluster operators and alert on any degraded components"

"Check MachineConfigPool status and show which nodes are being updated"

🔐 Security & Compliance

Ensure cluster security and certificate management:

"Scan all namespaces for expiring certificates and generate a renewal schedule"

"Investigate TLS certificate issues causing handshake failures in namespace istio-system"

"Audit all secrets and configmaps for sensitive data exposure patterns"

📈 Advanced Analytics & ML Insights

Leverage machine learning for pattern detection:

"Use streaming log analysis to process large log volumes from namespace data-pipeline with error pattern detection"

"Detect anomalies in log patterns using ML analysis with medium severity threshold for namespace api-gateway"

"Analyze resource utilization trends using Prometheus metrics and forecast capacity needs"

Configuration

Kubernetes Authentication

The server automatically detects Kubernetes configuration:

1. In-cluster config - When running inside a Kubernetes pod
2. Local kubeconfig - When running locally (uses ~/.kube/config)

Environment Variables

ML Model Persistence

The predictive_log_analyzer tool persists trained ML models and training data locally in ~/.lumino/. This enables model reuse across server restarts and incremental learning from historical failure patterns.

Directory Structure

~/.lumino/├── models/                     # Trained ML models│   ├── {model_id}.joblib       # Serialized model (e.g. IsolationForest via joblib)│   ├── {model_id}.meta.json    # Model metadata (created, last used, performance metrics)│   └── model_index.json        # Index tracking all models and the current active model└── training_data/              # Training data store    └── training_data.db        # SQLite database

Model IDs follow the pattern predictive_log_v1_YYYYMMDD_HHMMSS.

Training Data Database

The SQLite database (training_data.db) contains four tables:

All four tables define a cluster_id column for multi-cluster support. Currently, only log_samples and failure_labels actively populate it during writes; log_failure_correlations and training_runs leave it NULL. The cluster ID is derived from the active kubeconfig context name (e.g. api-stone-prod-p02-hjvn-p1-openshiftapps-com:6443) or falls back to in-cluster-{KUBERNETES_SERVICE_HOST} when running inside a pod.

Clearing Stale Data

Programmatic cleanup via the manage_prediction_training_data tool (action cleanup):

• cleanup_old_models(max_age_days=30, keep_min=3) -- removes models older than 30 days, always keeping the 3 most recent
• cleanup_old_data(max_age_days=90) -- removes log samples, failure labels, and correlations older than 90 days

Manual cleanup:

rm -rf ~/.lumino/              # Clear everything (models + training data)rm -rf ~/.lumino/models/       # Clear just modelsrm -rf ~/.lumino/training_data/ # Clear just training data (SQLite DB)

Disk usage note: Models accumulate over time. The default cleanup keeps models up to 30 days old with a minimum of 3 retained. Training data is kept for 90 days. Run the manage_prediction_training_data tool with action cleanup periodically to reclaim disk space.

KubeArchive Integration

KubeArchive stores Kubernetes resources off-cluster and provides a REST API for historical resource states and logs. LUMINO uses KubeArchive as a fallback when pods, PipelineRuns, or TaskRuns have been garbage-collected from the live cluster. The query_kubearchive tool queries this archive transparently.

Endpoint Auto-Discovery

The endpoint is discovered automatically using a 5-step chain (first match wins):

1. KUBEARCHIVE_HOST environment variable (highest priority)
2. OpenShift Route named kubearchive-api-server in namespaces: kubearchive, product-kubearchive, default
3. Kubernetes Ingress named kubearchive-api-server in the same namespaces
4. Kubernetes Service named kubearchive-api-server (in-cluster DNS: https://kubearchive-api-server.<namespace>.svc.cluster.local:<port>)
5. Kubeconfig-based Route inference -- constructs candidate URLs from the API server domain (pattern: https://kubearchive-api-server-{namespace}.apps.{cluster-domain}) and probes /livez

Results are cached at startup. On connection failure, the cache is cleared and re-probed on the next request.

Local Development (Port-Forwarding)

When running outside the cluster, if an in-cluster Service endpoint is discovered (step 4), LUMINO automatically sets up kubectl port-forward:

kubectl port-forward -n {namespace} svc/kubearchive-api-server {local_port}:{remote_port}

• Tries ports 8081--8090, then falls back to a system-assigned port
• The port-forward process is auto-started and auto-cleaned up on server exit
• If kubectl is not available, LUMINO logs a manual fallback command for the user

Authentication

KubeArchive authentication uses the following priority chain:

1. Provided token (from constructor / previous session)
2. In-cluster service account token (/var/run/secrets/kubernetes.io/serviceaccount/token)
3. Existing Kubernetes client token (extracted from the API client initialized at server startup)
4. OpenShift oc whoami -t token (for OpenShift clusters)
5. Auto-created short-lived service account token (kubectl create token, 1-hour duration, Kubernetes only)

Resource Management & Cleanup

The KubeArchiveEndpointDiscovery class implements robust subprocess cleanup for kubectl port-forward processes to prevent resource leaks.

Recommended Usage: Context Manager

Use the with statement for deterministic cleanup:

from src.helpers.kubearchive_integration import KubeArchiveEndpointDiscovery
with KubeArchiveEndpointDiscovery(k8s_core_api, k8s_custom_api) as discovery:    endpoint = await discovery.discover_endpoint()    # Use the endpoint...    # Port-forward subprocess automatically cleaned up on exit

Automatic Cleanup Layers

When used without explicit context management, the class provides three fallback cleanup mechanisms:

1. atexit handler — Cleans up port-forward on normal interpreter shutdown
2. Signal handlers (SIGTERM/SIGINT) — Graceful cleanup on termination, chains to original handlers
3. __del__ finalizer — Last-resort fallback (not guaranteed timing)

The context manager approach is preferred for deterministic resource cleanup.

KubeArchive Configuration

See the Configuration section above for KUBEARCHIVE_HOST and KUBEARCHIVE_ENABLED environment variables.

Prometheus/Thanos Integration

LUMINO auto-discovers Prometheus or Thanos Query endpoints for the prometheus_query, resource_bottleneck_forecaster, and ci_cd_performance_baselining_tool tools. Thanos Query implements the Prometheus HTTP API and is preferred when available since it provides a unified, deduplicated view across replicas.

Endpoint Discovery Priority

Auto-discovery order depends on runtime environment:

• In-cluster: Thanos services --> Prometheus services --> Prometheus Operator CRD --> OpenShift Routes
• Local/outside cluster: OpenShift Routes --> Thanos services --> Prometheus Operator CRD --> Prometheus services

Auto-Discovery Details

OpenShift Routes: Searches the openshift-monitoring namespace. Prefers the thanos-querier route over prometheus-k8s. Falls back to any route with prometheus in the name. Detects protocol from TLS termination config.

Thanos Services: Searches namespaces openshift-monitoring, monitoring, thanos, observability, kube-prometheus. Priority service names: thanos-query-frontend, thanos-querier, thanos-query. Also searches via label selectors: app.kubernetes.io/name=thanos-query, app.kubernetes.io/component=query,app.kubernetes.io/name=thanos, app=thanos-query, app=thanos-querier.

Prometheus Services: Searches namespaces openshift-monitoring, monitoring, prometheus, kube-prometheus, observability. Priority service names: prometheus-server, prometheus-k8s, prometheus. Also searches via label selectors: app=prometheus, app.kubernetes.io/name=prometheus, app.kubernetes.io/component=prometheus.

Prometheus Operator CRD: Discovers via monitoring.coreos.com/v1 Prometheus custom resources and their associated services (pattern: prometheus-{name} in the same namespace).

Prometheus/Thanos Authentication

Authentication for Prometheus/Thanos uses the following 5 methods in priority order:

1. oc whoami -t -- fresh OpenShift token (most reliable for OpenShift)
2. Re-read kubeconfig file for current token
3. In-memory Kubernetes client config token
4. ServiceAccount token file (/var/run/secrets/kubernetes.io/serviceaccount/token)
5. Environment variables: PROMETHEUS_TOKEN, OPENSHIFT_TOKEN, OC_TOKEN (checked in that order)

Configuration Example

{  "env": {    "THANOS_URL": "https://thanos-querier.example.com",    "PROMETHEUS_TOKEN": "your-bearer-token"  }}

Note: The endpoint cache has a 5-minute TTL. If you change THANOS_URL or PROMETHEUS_URL at runtime, the new value takes effect on the next query.

Available Tools

Kubernetes Core (5 tools)

Tekton Pipelines (6 tools)

Log Analysis (8 tools)

Event Analysis (3 tools)

Failure Analysis & RCA (2 tools)

Resource Monitoring (4 tools)

Namespace Investigation (2 tools)

Certificate & Security (2 tools)

OpenShift Specific (3 tools)

CI/CD Performance (2 tools)

Topology & Prediction (3 tools)

Simulation (1 tool)

Architecture

lumino-mcp-server/├── main.py                 # Entry point with transport detection├── src/│   ├── server-mcp.py       # MCP server with all 39 tools│   └── helpers/│       ├── constants.py              # Shared constants│       ├── event_analysis.py         # Event processing logic│       ├── failure_analysis.py       # RCA algorithms│       ├── kubearchive_integration.py # KubeArchive API client & discovery│       ├── log_analysis.py           # Log processing│       ├── ml_persistence.py         # ML model & training data storage│       ├── resource_topology.py      # Topology mapping│       ├── semantic_search.py        # NLP search│       └── utils.py                  # Utility functions└── pyproject.toml          # Project configuration

How It Works

LUMINO acts as a bridge between AI assistants and your Kubernetes infrastructure through the Model Context Protocol:

┌─────────────────────────────────────────────────────────────────┐│                        AI Assistant Layer                        ││          (Claude Desktop, Claude Code CLI, Gemini CLI)          │└────────────────────────────┬────────────────────────────────────┘                             │                             │ Natural Language Queries                             │ "Analyze failed pipelines"                             │ "Predict resource bottlenecks"                             ▼┌─────────────────────────────────────────────────────────────────┐│                     Model Context Protocol                       ││                      (MCP Communication)                         │└────────────────────────────┬────────────────────────────────────┘                             │                             │ Tool Invocations & Results                             │                             ▼┌─────────────────────────────────────────────────────────────────┐│                       LUMINO MCP Server                          ││  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐         ││  │ Log Analysis │  │ Event Intel  │  │  Predictive  │         ││  │   (6 tools)  │  │  (3 tools)   │  │  (2 tools)   │         ││  └──────────────┘  └──────────────┘  └──────────────┘         ││  ┌──────────────┐  ┌──────────────┐  ┌──────────────┐         ││  │   Pipeline   │  │  Simulation  │  │   Topology   │         ││  │  (6 tools)   │  │  (1 tool)    │  │  (2 tools)   │         ││  └──────────────┘  └──────────────┘  └──────────────┘         │└────────────────────────────┬────────────────────────────────────┘                             │                             │ Kubernetes API Calls                             │ Prometheus Queries                             │                             ▼┌─────────────────────────────────────────────────────────────────┐│                    Kubernetes/OpenShift Cluster                  ││                                                                   ││  ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐       ││  │   Pods   │  │ Services │  │ Tekton   │  │etcd/Logs │       ││  └──────────┘  └──────────┘  │Pipelines │  └──────────┘       ││  ┌──────────┐  ┌──────────┐  └──────────┘  ┌──────────┐       ││  │  Events  │  │ Configs  │  ┌──────────┐  │Prometheus│       ││  └──────────┘  └──────────┘  │OpenShift │  └──────────┘       ││                               │Operators │                       ││                               └──────────┘                       │└─────────────────────────────────────────────────────────────────┘

Workflow

1. User Query → AI assistant receives natural language request
2. MCP Translation → Assistant converts query to appropriate tool calls
3. LUMINO Processing → Server executes Kubernetes/Prometheus operations
4. Data Analysis → ML/statistical algorithms process raw data
5. AI Synthesis → Assistant formats results into human-readable insights

Key Features

• Minimal Local State - Queries cluster in real-time; optional ML model persistence in ~/.lumino/ for predictive analytics (see ML Model Persistence)
• Automatic Transport Detection - Switches between stdio (local) and HTTP (K8s) modes
• Token Budget Management - Adaptive strategies to handle large log volumes
• Intelligent Caching - Smart caching for frequently accessed data
• Security First - Uses existing kubeconfig RBAC permissions, no separate auth

MCP Client Integration

Method 1: Using MCPM (Recommended for Claude Code CLI / Gemini CLI)

The easiest way to install LUMINO MCP Server for Claude Code CLI or Gemini CLI is using MCPM - an MCP server package manager.

Install MCPM

# Clone and build MCPMgit clone https://github.com/spre-sre/mcpm.gitcd mcpmgo build -o mcpm .
# Optional: Add to PATHsudo mv mcpm /usr/local/bin/

Requirements: Go 1.23+, Git, Python 3.10+, uv (or pip)

Install LUMINO MCP Server

# Install from GitHub repository (short syntax)mcpm install @spre-sre/lumino-mcp-server
# Or use full GitHub URLmcpm install https://github.com/spre-sre/lumino-mcp-server.git
# For GitLab repositories (if hosted on GitLab)mcpm install gl:@spre-sre/lumino-mcp-server
# Install for specific clientmcpm install @spre-sre/lumino-mcp-server --claude  # For Claude Code CLImcpm install @spre-sre/lumino-mcp-server --gemini  # For Gemini CLI
# Install globally (works with both Claude and Gemini)mcpm install @spre-sre/lumino-mcp-server --global

Short syntax explained:

• @owner/repo - Installs from GitHub (default: https://github.com/owner/repo.git)
• gl:@owner/repo - Installs from GitLab (https://gitlab.com/owner/repo.git)
• Full URL - Works with any Git repository

This will:

• Clone the repository to ~/.mcp/servers/lumino-mcp-server/
• Auto-detect Python project and install dependencies using uv (or pip)
• Register with Claude Code CLI or Gemini CLI configuration automatically

Manage LUMINO

# List installed serversmcpm list
# Update LUMINOmcpm update lumino-mcp-server
# Remove LUMINOmcpm remove lumino-mcp-server

Method 2: Manual Configuration

If you prefer manual setup or need to configure Claude Desktop / Cursor, follow these client-specific guides:

Claude Desktop

1. Find your config file location:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json
   • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add LUMINO configuration:

{  "mcpServers": {    "lumino": {      "command": "uv",      "args": [        "run",        "--directory",        "/path/to/lumino-mcp-server",        "python",        "main.py"      ],      "env": {        "PYTHONUNBUFFERED": "1"      }    }  }}

3. Restart Claude Desktop

4. Verify: Look for the hammer icon (🔨) in Claude Desktop to see available tools

Claude Code CLI

Option A: Using MCPM (see Method 1 above)

Option B: Automatic Provisioning via Claude Code (Recommended and easiest way)

Copy and paste the provisioning prompt from the Quick Start section above into Claude Code. Claude will clone the repository, install dependencies, and configure the MCP server for your project.

Option C: Manual Configuration

1. Clone and install:

git clone https://github.com/spre-sre/lumino-mcp-server.gitcd lumino-mcp-serveruv sync  # Creates .venv with all dependencies

2. Create .mcp.json in your project root (for project-local config) or update ~/.claude.json (for global config):

{  "mcpServers": {    "lumino": {      "type": "stdio",      "command": "/absolute/path/to/lumino-mcp-server/.venv/bin/python",      "args": ["/absolute/path/to/lumino-mcp-server/main.py"],      "env": {        "PYTHONUNBUFFERED": "1"      }    }  }}

Important: Replace /absolute/path/to/lumino-mcp-server with the actual absolute path where you cloned the repository (e.g., /Users/username/projects/lumino-mcp-server).

3. Verify installation:

# Check MCP serversclaude mcp list
# Test with a queryclaude "List all namespaces in my cluster"

Gemini CLI

Option A: Using MCPM (Recommended - see Method 1 above)

Option B: Manual Configuration

1. Find your config file location:

   • macOS/Linux: ~/.config/gemini/mcp_servers.json
   • Windows: %APPDATA%\gemini\mcp_servers.json

2. Add LUMINO configuration:

{  "mcpServers": {    "lumino": {      "command": "uv",      "args": [        "run",        "--directory",        "/path/to/lumino-mcp-server",        "python",        "main.py"      ],      "env": {        "PYTHONUNBUFFERED": "1"      }    }  }}

3. Verify installation:

# Check MCP serversgemini mcp list
# Test with a querygemini "Show me failed pipeline runs"

Cursor IDE

1. Open Cursor Settings:

   • Press Cmd+, (macOS) or Ctrl+, (Windows/Linux)
   • Search for "MCP" or "Model Context Protocol"

2. Add MCP Server Configuration:

In Cursor's MCP settings, add:

{  "mcpServers": {    "lumino": {      "command": "uv",      "args": [        "run",        "--directory",        "/path/to/lumino-mcp-server",        "python",        "main.py"      ],      "env": {        "PYTHONUNBUFFERED": "1"      }    }  }}

Alternative - Using Cursor's settings.json:

1. Open Command Palette (Cmd+Shift+P or Ctrl+Shift+P)
2. Type "Preferences: Open User Settings (JSON)"
3. Add the MCP configuration:

{  "mcp.servers": {    "lumino": {      "command": "uv",      "args": [        "run",        "--directory",        "/path/to/lumino-mcp-server",        "python",        "main.py"      ],      "env": {        "PYTHONUNBUFFERED": "1"      }    }  }}

3. Restart Cursor IDE

4. Verify: Open Cursor's AI chat and check if LUMINO tools are available

Configuration Notes

Replace /path/to/lumino-mcp-server with the actual path where you cloned the repository:

# Example paths:# macOS/Linux: /Users/username/projects/lumino-mcp-server# Windows: C:\Users\username\projects\lumino-mcp-server
# If installed via MCPM:# ~/.mcp/servers/lumino-mcp-server/

Environment Variables (optional):

Add these to the env section if needed:

{  "env": {    "PYTHONUNBUFFERED": "1",    "KUBERNETES_NAMESPACE": "default",    "PROMETHEUS_URL": "http://prometheus:9090",    "LOG_LEVEL": "INFO"  }}

Using Alternative Python Package Managers

With pip instead of uv

{  "command": "python",  "args": [    "/path/to/lumino-mcp-server/main.py"  ]}

Note: Ensure you've activated the virtual environment first:

cd /path/to/lumino-mcp-serverpython -m venv venvsource venv/bin/activate  # On Windows: venv\Scripts\activatepip install -e .

With poetry

{  "command": "poetry",  "args": [    "run",    "python",    "main.py"  ],  "cwd": "/path/to/lumino-mcp-server"}

Testing Your Configuration

After configuring any client, test the connection:

1. Check if tools are loaded:

   • Claude Desktop: Look for 🔨 hammer icon
   • Claude Code CLI: claude mcp list
   • Gemini CLI: gemini mcp list
   • Cursor: Check AI chat for available tools

2. Test a simple query:

"List all namespaces in my Kubernetes cluster"

3. Check server logs (if issues):

# Run server manually to see errorscd /path/to/lumino-mcp-serveruv run python main.py

Expected output:

MCP Server running in stdio modeAvailable tools: 39Waiting for requests...

Advanced Configuration

Multiple Clusters

Configure multiple LUMINO instances for different clusters:

{  "mcpServers": {    "lumino-prod": {      "command": "uv",      "args": ["run", "--directory", "/path/to/lumino-mcp-server", "python", "main.py"],      "env": {        "KUBECONFIG": "/path/to/prod-kubeconfig.yaml"      }    },    "lumino-dev": {      "command": "uv",      "args": ["run", "--directory", "/path/to/lumino-mcp-server", "python", "main.py"],      "env": {        "KUBECONFIG": "/path/to/dev-kubeconfig.yaml"      }    }  }}

Custom Log Level

{  "env": {    "LOG_LEVEL": "DEBUG",    "MCP_SERVER_LOG_LEVEL": "DEBUG"  }}

Supported Transports

The server automatically detects the appropriate transport:

• stdio - For local desktop integrations (Claude Desktop, Claude Code CLI, Gemini CLI, Cursor)
• streamable-http - For Kubernetes deployments (when KUBERNETES_NAMESPACE is set)

Performance Considerations

Optimizing for Large Clusters

LUMINO is designed to handle clusters of any size efficiently:

Token Budget Management

LUMINO automatically manages AI context limits:

• Adaptive Sampling - Smart tools auto-sample data when volumes are high
• Progressive Loading - Stream analysis processes data in chunks
• Token Budgets - Configurable limits prevent context overflow
• Hybrid Strategies - Automatically selects best analysis approach

Query Optimization Tips

Use Namespace Filtering

✅ "Analyze logs for pods in namespace production"❌ "Analyze all pod logs in the cluster"

Specify Time Windows

✅ "Show events from the last 2 hours"❌ "Show all events" (might return thousands)

Leverage Smart Tools

✅ "smart_summarize_pod_logs" - Adaptive analysis❌ Direct log dumps - No processing

Use Progressive Analysis

✅ Start with "overview" → drill down to "detailed"❌ Jump directly to "deep_dive" on large datasets

Performance Metrics

Caching Strategy

LUMINO uses intelligent caching for frequently accessed data:

• 15-minute cache - For web-fetched content
• Session cache - For hybrid log analysis
• ML model persistence - Predictive models and training data stored locally in ~/.lumino/ (see ML Model Persistence)

Concurrent Requests

The server handles multiple concurrent requests efficiently:

• Thread-safe operations - Safe parallel tool execution
• Connection pooling - Reuses Kubernetes API connections
• Async HTTP - Non-blocking Prometheus queries

Resource Usage

Server Resource Requirements

Note: LUMINO requires minimal resources. ML models and training data are persisted locally in ~/.lumino/ (see ML Model Persistence). Most processing happens in the AI assistant.

Troubleshooting

Common Issues

No Kubernetes cluster found

Error: Unable to load kubeconfig

Ensure you have a valid kubeconfig at ~/.kube/config or are running inside a cluster.

Permission denied for resources

Error: Forbidden - User cannot list resource

Check your RBAC permissions. The server needs read access to the resources you want to query.

Tool timeout For large clusters, some tools may timeout. Use filtering options (namespace, labels) to reduce scope.

Dependencies

• mcp[cli]>=1.10.1 - Model Context Protocol SDK
• kubernetes>=32.0.1 - Kubernetes Python client
• pandas>=2.0.0 - Data analysis
• scikit-learn>=1.6.1 - ML algorithms
• prometheus-client>=0.22.0 - Prometheus integration
• aiohttp>=3.12.2 - Async HTTP client

Contributing

Contributions are welcome! Please read our Contributing Guide before submitting pull requests.

Security

For security vulnerabilities, please see our Security Policy.

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Acknowledgments

• Built with FastMCP framework
• Inspired by the needs of SRE teams managing complex Kubernetes environments