Connects AI assistants to Kubernetes clusters running Flux Operator, enabling GitOps analysis, troubleshooting, debugging pipelines, root cause analysis for failed deployments, comparison of configurations, visualization of dependencies, and instruction of Flux operations through natural language.
Supports integration with GitHub Copilot, enabling it to interact with Flux and Kubernetes clusters through the MCP Server.
Provides access to Kubernetes clusters, allowing AI assistants to analyze resources, compare configurations between clusters, and troubleshoot deployments in the context of GitOps workflows.
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., "@FluxCD MCP Server show me all failed deployments in the last hour"
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.
The Flux MCP Server connects AI assistants directly to your Kubernetes clusters running Flux Operator, enabling GitOps analysis and troubleshooting through natural language.
Using AI assistants with the Flux MCP Server, you can:
Debug GitOps pipelines end-to-end from Flux resources to application logs
Get intelligent root cause analysis for failed deployments
Compare Flux configurations and Kubernetes resources between clusters
Visualize Flux dependencies with diagrams generated from the cluster state
Instruct Flux to perform operations using conversational prompts
Install the Flux MCP Server using Homebrew:
brew install controlplaneio-fluxcd/tap/flux-operator-mcpFor other installation options, refer to the installation guide.
Add the following configuration to your AI assistant's MCP settings:
{
"flux-operator-mcp":{
"command":"flux-operator-mcp",
"args":[
"serve",
"--read-only=false"
],
"env":{
"KUBECONFIG":"/path/to/.kube/config"
}
}
}Replace /path/to/.kube/config with the absolute path to your kubeconfig file,
you can find it with: echo $HOME/.kube/config.
The MCP Server advertises built-in instructions to the AI assistant during initialization. For step-by-step troubleshooting procedures, copy the AI rules from instructions.md and place them into the appropriate file for your assistant.
Restart the AI assistant app and test the MCP Server with the following prompts:
"Which cluster contexts are available in my kubeconfig?"
"What version of Flux is running in my current cluster?"
For more information on how to use the MCP Server with Claude, Cursor, GitHub Copilot, and other assistants, please refer to the documentation website.
Related MCP server: mctl
We welcome contributions to the Flux MCP Server project via GitHub pull requests. Please see the CONTRIBUTING guide for details on how to set up your development environment and start contributing to the project.
The MCP Server is open-source and part of the Flux Operator project licensed under the AGPL-3.0 license.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Fail-closed policy guardrails for AI agents running kubectl, terraform, helm, and argocd.
Deploy applications to Cloud Run
AI-native git hosting — repos, PRs, issues, CI gates, and AI code review over MCP (60 tools).
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/controlplaneio-fluxcd/flux-operator'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
