Dev/Infra

MCP server that gives LLMs full control over local Kubernetes dev environments. Built in Go, it exposes 63 tools across 8 groups for managing k3d clusters, kubectl operations, Helm charts, Kustomize overlays, Tilt dev workflows, Artifact Hub lookups, and documentation search.

- k3d(9 tools) — create, delete, start, stop, list clusters and nodes
- kubectl(16 tools) — get, describe, apply, delete, logs, port-forward, raw command escape hatch
- Helm(10 tools) — install, upgrade, uninstall, template, status, show values/chart, repo management (via Go SDK)
- Kustomize(5 tools) — build, build-and-apply, edit image/namespace, list resources (via Go API)
- Tilt(10 tools) — up, down, ci, logs, status, get, describe, trigger, session (queries via HTTP API)
- Artifact Hub(6 tools) — search, package info, values, schema, readme, templates
- Doc search(4 tools) — full-text search over tilt, k3d, kubectl, and Helm docs (Bleve index, 257+ pages)
- CI(3 tools) — composite bootstrap, teardown, and diagnostic collection

Hybrid approach — each tool group uses the best integration method:

- Go1.26+
- Docker(for k3d clusters)
- k3d— local Kubernetes clusters
- kubectl— cluster interaction
- tilt— dev workflow orchestration
- HelmandKustomizeare optional at the CLI level (Go SDKs are embedded)

# Build the binary make build # Run over stdio (default MCP transport) ./bin/devinfra-mcp # Run as HTTP server ./bin/devinfra-mcp --http --addr :8080 # With a config file ./bin/devinfra-mcp --config settings.json

Add to.mcp.jsonin your project root (or~/.claude.jsonfor global):

{ "mcpServers": { "devinfra-mcp": { "command": "devinfra-mcp", "args": ["--config", "/path/to/settings.json"] } } }

Add to.cursor/mcp.jsonin your project root (or~/.cursor/mcp.jsonfor global):

{ "mcpServers": { "devinfra-mcp": { "command": "devinfra-mcp", "args": ["--config", "/path/to/settings.json"] } } }

Add to.codex/config.tomlin your project root (or~/.codex/config.tomlfor global):

[mcp_servers.devinfra-mcp] command = "devinfra-mcp" args = ["--config", "/path/to/settings.json"]

Instead of stdio, you can run the server over HTTP for clients that support remote MCP servers:

./bin/devinfra-mcp --http --addr :8080 --config settings.json

Create a JSON config file to override defaults.The config must be valid JSON — no comments are allowed.

{ "kubeconfig": "", "default_context": "", "blocked_contexts": ["production", "staging-"], "tilt_api": "", "kubectl_apply_dry_run_default": "client", "doc_index_path": "~/.devinfra-mcp/docs.bleve", "doc_sources": { "tilt": "github.com/tilt-dev/tilt.build/docs", "k3d": "github.com/k3d-io/k3d/docs", "k8s": "embedded" }, "timeouts": { "default": "30s", "logs": "10s", "apply": "60s", "cluster_create": "120s", "tilt_ci": "300s" }, "artifacthub": { "enabled": true, "base_url": "https://artifacthub.io/api/v1", "cache_ttl": "1h", "prefer_verified_publisher": true, "auto_lookup_on_install": true, "timeout": "10s" } }

- kubectl_applydefaults todry_run: "client"— real apply requires explicitdry_run: "none"
- Blocked contexts (e.g.,production,staging-) reject operations at the safety layer
- kubectl_rawvalidates args against a denylist; override requiresunsafe: true
- kubectl_logs --followis capped at 10 seconds

The server includes an embedded Bleve full-text search index over 4 documentation sources:

# Clone doc sources (uses sparse checkout for large repos) make docs-clone # Build the Bleve search index make docs-index

make build # Build binary to bin/devinfra-mcp make test # Unit tests make test-integration # Integration tests (needs Docker) make e2e # Full e2e: create k3d cluster, test, teardown make lint # golangci-lint make vet # go vet make check # vet + lint + test

Reusable workflow templates the LLM can invoke for multi-step operations:

Read-only data the LLM can pull into context:

cmd/devinfra-mcp/main.go Entry point, wires all components internal/ executor/ Shell-out abstraction (all CLI calls go through here) tools/ 63 MCP tools across 8 groups k3d.go, kubectl.go, helm.go, kustomize.go, tilt.go, artifacthub.go, docsearch.go, ci.go helmclient/ Helm Go SDK wrapper (Client interface + mock) kustomizeclient/ Kustomize Go API wrapper (Client interface + mock) tilt/ Tilt HTTP API client (Client interface + mock) artifacthub/ Artifact Hub HTTP client with response caching docsearch/ Bleve index builder + markdown scraper config/ JSON config loading with defaults safety/ Context blocklist, input sanitization prompts/ MCP prompt templates resources/ MCP resource providers (cluster state, docs)

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Official Docker MCP Toolkit for discovering, configuring, and running containerized MCP servers through Docker Desktop and the Docker MCP gateway.

The Octopus MCP Server provides your AI assistant with powerful tools that allow it to inspect, query, and diagnose problems within your Octopus instance, transforming it into your ultimate DevOps wingmate.

The Railway MCP Server enables natural language interaction with your Railway projects and infrastructure. Ask your IDE or AI assistant to create projects, deploy templates, manage environments, pull variables, redeploy services, and more.

The Shipyard CLI provides an MCP server for agents to manage Shipyard environments directly: by pulling logs, comparing branches, running tests, and stopping/starting environments..

MCP server for managing Unleash feature flags and automate best practices.

A secure, Docker-based server providing core execution capabilities for AI agents.

Integrates with AWS CodePipeline to manage continuous integration and delivery pipelines.

Manage apps, builds, and artifacts on Bitrise, a Continuous Integration and Delivery (CI/CD) platform.

Hot reload remote containerized Python applications directly from your IDE.