Documentation Index
Fetch the complete documentation index at: https://docs.controlplane.com/llms.txt
Use this file to discover all available pages before exploring further.
The Control Plane MCP Server enables AI assistants and tools to interact directly with your Control Plane infrastructure. Using the Model Context Protocol (MCP), you can create, manage, and deploy resources through natural language conversations.
What is MCP?
The Model Context Protocol (MCP) is an open standard that allows AI models to securely connect to external tools and data sources. With the Control Plane MCP Server, AI assistants can:
Quick Start
MCP Server Endpoint
Authentication
The MCP Server requires authentication via a service account token. Include the token in the Authorization header:
Authorization: <your-service-account-token>
The Control Plane MCP Server works with any AI assistant or development tool that supports remote MCP servers. Below are setup guides for popular tools:
Service Account Permissions
The MCP Server respects all Control Plane policies and permissions. Your service account’s capabilities depend on the groups and policies assigned to it.
Built-in Groups
Control Plane provides two built-in groups for common permission patterns:
| Group | Permissions | Use Case |
|---|---|---|
| viewers | view on all resources | Read-only exploration, querying infrastructure status |
| superusers | manage on all resources | Full automation, creating and modifying all resources |
Custom Permissions
For more granular control, you can:
- Create custom groups with specific members
- Define policies that grant targeted permissions
- Assign your service account to groups that match your use case
Recommended Approaches
| Use Case | Recommended Setup |
|---|---|
| Quick exploration | Add service account to viewers group |
| Full development access | Add service account to superusers group |
| Production automation | Create custom group with specific policies for required resources |
| Team-specific access | Create group per team with policies scoped to their GVCs |
How It Works
When an AI assistant connects to the MCP Server, it follows this initialization flow:
Available Resources
The MCP Server provides these resources for AI assistants to load context:
| Resource | URI | Description |
|---|---|---|
| Guide | cpln+virtual://guide | MCP usage guide with tool taxonomy and best practices |
| About | cpln+virtual://about | Server metadata, version, and capability summary |
| CLI Guide | cpln+virtual://cli/guide | CLI reference for cpln commands |
| Canon | cpln+virtual://canon | CLI patterns, API canon, and guardrails |
| Docs (Concise) | cpln+virtual://docs/concise | LLM-friendly platform overview |
| Docs (Full) | cpln+virtual://docs/full | Complete documentation reference |
| OpenAPI | cpln+virtual://openapi | Control Plane OpenAPI specification |
| Templates | cpln+virtual://templates/{kind} | Quick-start resource templates |
Available Prompts
The MCP Server includes curated prompts for common workflows:
| Prompt | Description |
|---|---|
| General Assistant | Overall platform guidance and operations |
| GVC Operations | GVC creation, management, and location configuration |
| Workload Deployment | Container deployment, scaling, and configuration |
| Secret Patterns | Secret injection and workload access patterns |
| Troubleshooting | Debugging workload issues and failures |
| Image Management | Container image registry operations |
| Expert Assistant | Advanced platform engineering scenarios |
| Platform Engineer | Infrastructure design and architecture |
Best Practices
Recommended Prompts Structure
For the best results, structure your prompts with:
- Context: Org and GVC
- Action: What you want to do
- Target: Which resource
- Details: Specific configuration values