Dot AI

Get detailed status of a Helm release including deployment status, notes, and resource state. Use to check if a release is healthy or diagnose issues like stuck pending-upgrade states.

Render Helm chart templates locally and return the YAML output. Does not require cluster access.

Uninstall a Helm release and remove all associated Kubernetes resources.

Analyze the blast radius of a proposed Kubernetes operation. Accepts free-text input: kubectl commands (e.g., "kubectl delete pvc data-postgres-0 -n production"), YAML manifests, or plain-English descriptions (e.g., "what happens if I delete the postgres database?"). Returns whether the operation is safe and a detailed dependency analysis with confidence levels.

Split a document into semantic chunks with deterministic IDs. Chunks are split at natural boundaries (paragraphs, sentences, words) with configurable size and overlap. Each chunk gets a deterministic UUID v5 based on the source URI and chunk index.

Get list of all available Kubernetes API resources in the cluster (resource types, API groups, namespaced vs cluster-scoped). Use this to discover what resources are available before querying specific resources. Essential for understanding what can be investigated in this cluster.

Apply a YAML manifest to create or update Kubernetes resources. This executes the actual apply command (not dry-run). Use kubectl_apply_dryrun first to validate.

Validate that a kubectl apply command will be accepted by the cluster without actually applying it. Use this to test applying YAML manifests or configuration changes before completing investigation.

Delete Kubernetes resources by kind and name, or from a YAML manifest. This executes the actual delete command (not dry-run). Use kubectl_delete_dryrun first to validate.

Validate that a kubectl delete command will be accepted by the cluster without actually deleting resources. Use this to test resource deletion before completing investigation.

Get detailed information about specific Kubernetes resources including configuration, status, events, and relationships. Use this when you need comprehensive details about a specific resource, especially to understand configuration issues or see recent events related to that resource.

Get Kubernetes events which record important state changes, errors, warnings, and informational messages from the cluster. Essential for understanding scheduling issues, resource problems, configuration errors, and system-level events affecting resources.

Execute a kubectl command with the given arguments. Use for remediation commands like scale, rollout restart, label, annotate, etc. Only use for user-approved actions.

Get Kubernetes resources and their current state in TABLE FORMAT (most efficient). Returns compact table with NAME, STATUS, READY, AGE columns. Use this to list resources and check basic status. For detailed information, use kubectl_describe instead. IMPORTANT: Always returns table format - output format flags like -o=yaml or -o=json are automatically stripped.

Get the OpenAPI v3 schema for a Custom Resource Definition (CRD). Use this to understand the structure, required fields, validation rules, and available properties when crafting patches or configurations for custom resources like CNPG clusters, Crossplane resources, ArgoCD applications, etc.

Get printer columns for a resource type. INTERNAL USE ONLY - used by capability scanning to discover how resources are displayed.

Get a single Kubernetes resource as structured JSON with full metadata, spec, and status. Use this when you need programmatic access to resource configuration and state, such as analyzing ownerReferences, checking exact spec values, or examining detailed status conditions. Returns the complete resource object.

Get container logs from pods. Essential for debugging application crashes, errors, and understanding runtime behavior. Use --previous flag to get logs from crashed/restarted containers.

Patch a Kubernetes resource using strategic merge patch, JSON merge patch, or JSON patch. This executes the actual patch command (not dry-run). Use kubectl_patch_dryrun first to validate.

Validate that a kubectl patch command will be accepted by the cluster without actually applying it. Use this to test your proposed remediation patches before completing investigation. Essential for confirming command syntax and cluster acceptance.

Get Kubernetes client and server version information. Returns JSON with clientVersion and serverVersion objects containing gitVersion, platform, goVersion, and other version details.

Manage the knowledge base: ingest documents, search with natural language, or delete chunks. Use "ingest" to store organizational documentation, "search" to find relevant content semantically, or "deleteByUri" to remove all chunks for a document. TIP: For complex questions, you can call search multiple times with different phrasings to gather comprehensive information before synthesizing your answer.

Tool for managing cluster resource capabilities. Supports scan, list, get, search, delete, deleteAll, and progress operations for cluster resource capability discovery and management. Use dataType="capabilities" to manage cluster capabilities. NOTE: Organizational patterns and policies are now managed via manageKnowledge tool (ingest documents, search, deleteByUri) with automatic AI classification.

AI-powered Kubernetes application operations tool for Day 2 operations. Handles updates, scaling, enhancements, rollbacks, and deletions through natural language intents. Analyzes current state, applies organizational patterns and policies, validates changes via dry-run, and executes approved operations safely.

Setup project, audit repository, or generate repository files. Use this when user wants to: setup project, audit repo, check missing files, create README, add LICENSE, generate CONTRIBUTING.md, add CI/CD workflows, initialize documentation, setup governance files. Analyzes local repositories and generates missing configuration, documentation, and governance files. Does NOT handle Kubernetes deployments - use recommend for those.

Natural language query interface for Kubernetes cluster intelligence. Ask any questions about your cluster resources, capabilities, and status in plain English. Examples: "What databases are running?", "Describe the nginx deployment", "Show me pods in the kube-system namespace", "What operators are installed?", "Is my-postgres healthy?"

Query capabilities using Qdrant filter syntax. Use this when you need to filter by specific fields like provider, complexity, or group - NOT for semantic/conceptual searches. Available payload fields for filtering: - resourceName: string (e.g., "Deployment", "StatefulSet", "Cluster") - group: string (e.g., "apps", "postgresql.cnpg.io", "apiextensions.crossplane.io") - apiVersion: string (e.g., "apps/v1", "postgresql.cnpg.io/v1") - providers: string[] (e.g., ["kubernetes", "crossplane", "cnpg"]) - complexity: string ("low", "medium", "high") - capabilities: string[] (e.g., ["stateless-workload…

Query cluster resources using Qdrant filter syntax. Use this when you need to filter by specific fields like kind, namespace, or labels. This is the primary tool for finding resource instances after using search_capabilities to identify relevant kinds. Available payload fields for filtering: - id: string (format: namespace:apiVersion:kind:name) - namespace: string (e.g., "default", "kube-system", "_cluster" for cluster-scoped) - name: string (resource name) - kind: string (e.g., "Deployment", "Service", "Pod", "StatefulSet") - apiVersion: string (e.g., "apps/v1", "v1") - apiGroup: string (e.…

Deploy applications, infrastructure, and services using Kubernetes resources with AI recommendations. Supports cloud resources via operators like Crossplane, cluster management via CAPI, and traditional Kubernetes workloads. Describe what you want to deploy. Does NOT handle policy creation, organizational patterns, or resource capabilities - use manageOrgData for those.

AI-powered Kubernetes issue analysis that provides root cause identification and actionable remediation steps. Unlike basic kubectl commands, this tool performs multi-step investigation, correlates cluster data, and generates intelligent solutions. Use when users want to understand WHY something is broken, not just see raw status. Ideal for: troubleshooting failures, diagnosing performance issues, analyzing pod problems, investigating networking/storage issues, or any "what's wrong" questions.

Semantic search for cluster capabilities. Use this to find what KINDS of resources relate to a concept (e.g., "database" returns StatefulSet, CNPG Cluster, Crossplane RDS). Returns capability definitions with semantic meaning, not actual resource instances. This tool is essential for the "semantic bridge" pattern: 1. User asks about a concept (e.g., "databases", "message queues", "web servers") 2. This tool finds which resource KINDS relate to that concept 3. Then use query_resources or kubectl_get to find actual instances of those kinds Example: "database" might return capabilities for Stat…

Search the knowledge base for relevant information. Returns chunks of text from documents that match the query semantically.

Search for Kubernetes resources in the cluster inventory using semantic search. Searches resource names, kinds, labels, and annotations stored in Vector DB. This tool is useful for: - Finding resources by partial name match (e.g., "nginx" finds nginx-deployment, nginx-service) - Finding resources by kind (e.g., "deployments" finds all Deployment resources) - Finding resources by label values (e.g., "frontend" finds resources with tier=frontend label) - Finding resources by annotation content (e.g., "team platform" finds resources with team=platform annotation) You can optionally filter resul…

Execute a shell command in the plugin container. Used for running validated remediation commands. The command is executed exactly as provided.

Manage users (create, list, delete)

Validates Mermaid diagram syntax. Use this tool to check if a Mermaid diagram has correct syntax BEFORE including it in visualizations. IMPORTANT: Always validate all Mermaid diagrams before returning them. If validation fails, fix the error and validate again. Common Mermaid syntax errors to watch for: - "classDist" should be "classDef" (class definition) - Missing quotes around labels with special characters - Invalid node/edge syntax - Unbalanced brackets or parentheses Returns: - valid: boolean - true if diagram is valid - error: string | null - error message if invalid, null if valid -…

Count documents in a collection without fetching their payloads. Uses the Qdrant count API, so it stays cheap regardless of collection size.

Delete a document by its ID from a collection.

Delete all documents from a collection. Preserves the collection structure (schema, indexes) but removes all points.

Retrieve a single document by its ID, including its vector and payload.

List documents from a collection with optional filtering.

Query documents using Qdrant filter conditions. Does not require an embedding vector.

Search for similar documents using vector similarity. Requires a pre-computed embedding vector.

Search for documents using keyword matching. Scores results based on keyword matches in searchText and triggers fields. Does not require an embedding vector.

Store a document with its vector embedding. Upserts if document with same ID exists.

Get comprehensive system health and diagnostics

Deploy a web application with service and ingress