OpenShift LightSpeed MCP Server
Provides tools for interacting with OpenShift LightSpeed, enabling AI-powered OpenShift assistance and troubleshooting through Red Hat's OpenShift platform.
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., "@OpenShift LightSpeed MCP ServerHelp me troubleshoot a pod that's failing to start"
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.
OpenShift LightSpeed MCP Server
A Model Context Protocol (MCP) server that integrates OpenShift LightSpeed capabilities with Claude Code, enabling AI-powered OpenShift assistance and troubleshooting.
Overview
This MCP server provides Claude Code with access to OpenShift LightSpeed, allowing users to get expert OpenShift guidance, troubleshooting help, and best practices directly within their development workflow.
Related MCP server: Ambient Code Platform MCP Server
Features
OpenShift Expertise: Get answers to OpenShift-related questions and troubleshooting guidance
Seamless Integration: Works directly within Claude Code for enhanced development experience
Configurable: Flexible configuration for different OpenShift LightSpeed deployments
Error Handling: Robust error handling and timeout management
Installation
Prerequisites
Python 3.12+
uv package manager
Access to an OpenShift LightSpeed API endpoint
Setup
Clone and install dependencies:
cd ols-mcp uv syncConfigure environment:
cp .env.example .env # Edit .env with your OLS API configurationTest the server:
uv run python -m ols_mcp.server
Configuration
Environment Variables
Configure the server using environment variables or a .env file:
Variable | Description | Default |
| OpenShift LightSpeed API endpoint |
|
| Bearer token for authentication | None (required for most deployments) |
| Request timeout in seconds |
|
| SSL certificate verification |
|
Example .env file:
OLS_API_URL=https://your-ols-instance.com
OLS_API_TOKEN=your-bearer-token-here
OLS_TIMEOUT=30.0
OLS_VERIFY_SSL=trueClaude Code Integration
To use this MCP server with Claude Code, add it to your Claude Code configuration:
Configuration File Location
Linux/macOS:
~/.config/claude-code/config.jsonWindows:
%APPDATA%\claude-code\config.json
Configuration Example
Add the following to your config.json:
{
"mcpServers": {
"openshift-lightspeed": {
"command": "uv",
"args": ["run", "python", "-m", "ols_mcp.server"],
"cwd": "/path/to/your/ols-mcp",
"env": {
"OLS_API_URL": "https://your-ols-instance.com",
"OLS_API_TOKEN": "your-token-here",
"OLS_TIMEOUT": "30.0",
"OLS_VERIFY_SSL": "true"
}
}
}
}Important: Update the cwd path to point to your actual ols-mcp directory.
Verification
Restart Claude Code after adding the configuration
The
openshift-lightspeedtool should now be availableTest with OpenShift-related questions
Usage Examples
Once integrated with Claude Code, you can ask questions like:
"Help me troubleshoot a pod that's failing to start"
"How do I scale a deployment in OpenShift?"
"My application is getting 503 errors, what should I check?"
"Show me how to create a route for my service"
"What's the best way to configure resource limits?"
Claude Code will automatically use the OpenShift LightSpeed MCP server to provide expert OpenShift guidance.
Development
Project Structure
ols-mcp/
├── pyproject.toml # uv project configuration
├── .env.example # Environment configuration template
├── src/ols_mcp/
│ ├── __init__.py
│ ├── models.py # Pydantic models for requests/responses
│ ├── client.py # HTTP client for OLS API communication
│ └── server.py # MCP server implementation
└── README.md # This fileAvailable Tools
The server provides the following MCP tool:
openshift-lightspeed: Submit queries to OpenShift LightSpeed and receive expert guidance
Error Handling
The server includes comprehensive error handling for:
Network connectivity issues
API authentication failures
Timeout scenarios
Invalid responses
SSL certificate problems
Troubleshooting
Common Issues
Connection Refused: Check that
OLS_API_URLis correct and the service is runningAuthentication Errors: Verify your
OLS_API_TOKENis valid and has proper permissionsSSL Errors: For self-signed certificates, set
OLS_VERIFY_SSL=falseTimeout Issues: Increase
OLS_TIMEOUTfor slower networks
Debug Mode
Run the server with debug logging:
DEBUG=1 uv run python -m ols_mcp.serverContributing
This project uses:
uv for dependency management
Pydantic for data validation
httpx for HTTP client functionality
MCP SDK for protocol implementation
License
This project is part of the OpenShift ecosystem and follows Red Hat's open source practices.
Available Tools
1 toolopenshift-lightspeedB
Query OpenShift LightSpeed for assistance with OpenShift, Kubernetes, and related technologies
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question or query to send to OpenShift LightSpeed | |
| conversation_id | No | Optional conversation ID for maintaining context across queries |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It only says 'Query...for assistance', implying a read operation but not explicitly stating side effects, authentication needs, or response behavior. Minimal disclosure beyond the obvious.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded with the key action and resource. No wasted words; it is appropriately concise for a simple query tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with two parameters and no output schema, the description is adequate but lacks any hint about return format or typical usage. It meets minimum viability but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with both parameters described in the schema. The tool description adds no additional meaning beyond what is already in the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Query' and resource 'OpenShift LightSpeed', specifying the domain of OpenShift, Kubernetes, and related technologies. It is specific and unambiguous despite the absence of siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool or when alternatives might be more appropriate. There is no mention of prerequisites, context, or limitations, leaving the agent without usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
1 tool update
v0.1.0- First observed
openshift-lightspeed
TDQS
With only one tool, there is no possibility of confusion or overlap, making disambiguation perfect.
A single tool name cannot be inconsistent; it follows its own pattern, so consistency is perfect.
One tool is too few for a server presumably handling OpenShift and Kubernetes queries; the scope feels thin and limiting for agents.
Only a generic query tool exists, with no support for specific operations (e.g., listing, creating, updating resources), so the surface is severely incomplete.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Deploy, monitor, and manage your OpenClaw AI assistants via natural language.
Connect Claude AI to UluP Spaces via MCP — create projects, nodes, and tasks with OAuth 2.0.
Use AI models for chat, image, and video generation from Claude Code and other MCP hosts.
- platform7nOAuthtech.p7n
Connect Claude to your Platform7n workspaces — chat, links, and tasks. One-click OAuth.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables delegation of agentic sessions to Kubernetes-hosted Claude agents running on the Ambient Code Platform. Supports creating, managing, and communicating with remote AI agent sessions through OpenShift authentication.-
- FlicenseAqualityBmaintenanceDelegates expensive or long-running AI tasks to Kubernetes-hosted Claude agents running on OpenShift. Enables creating, managing, and monitoring remote agentic sessions for complex work like codebase analysis and security audits.41-
- AlicenseBqualityCmaintenanceIntegrates with IBM watsonx.ai to enable Claude Code to delegate text generation, chat, embeddings, and model listing to IBM foundation models like Granite and Llama.1368MIT
- AlicenseNot gradedqualityDmaintenanceEnables natural language Kubernetes cluster operations, SLO monitoring, and PromQL queries via Claude using the Model Context Protocol.1MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/thoraxe/ols-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server