terrashark MCP — Cas d'usage, Installer & Démo en direct

Pourquoi l'utiliser

Fonctionnalités clés

Grounded in HashiCorp Terraform best practices
Eliminates hallucinated resource arguments
Modular structure by default (modules/, envs/)
Security-first defaults (least privilege, encryption on)
State layout guidance (remote backend, workspace patterns)
Works with Claude Code and Codex

Démo en direct

Aperçu en pratique

terrashark-skill.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "terrashark-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/LukasNiessen/terrashark",
        "~/.claude/skills/terrashark"
      ],
      "_inferred": true
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "terrashark-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/LukasNiessen/terrashark",
        "~/.claude/skills/terrashark"
      ],
      "_inferred": true
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "terrashark-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/LukasNiessen/terrashark",
        "~/.claude/skills/terrashark"
      ],
      "_inferred": true
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "terrashark-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/LukasNiessen/terrashark",
        "~/.claude/skills/terrashark"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "terrashark-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/LukasNiessen/terrashark",
        "~/.claude/skills/terrashark"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

{
  "context_servers": {
    "terrashark-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/LukasNiessen/terrashark",
          "~/.claude/skills/terrashark"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

claude mcp add terrashark-skill -- git clone https://github.com/LukasNiessen/terrashark ~/.claude/skills/terrashark

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : terrashark

How to scaffold a production-grade AWS VPC module

👤 Platform engineers starting a new environment ⏱ ~45 min intermediate

Quand l'utiliser : Day one of a new AWS account; you want a VPC module that won't embarrass you in 6 months.

Prérequis

Skill installed — git clone https://github.com/LukasNiessen/terrashark ~/.claude/skills/terrashark
terraform CLI 1.6+ — brew install terraform

Déroulement

Generate module

Use terrashark. AWS VPC module, 3 AZs, public + private + db subnets, NAT gateways per AZ, flow logs on.✓ Copié

→ Module with variables.tf, main.tf, outputs.tf — no hallucinated args
Add security defaults

Ensure default security group denies all, flow logs go to CloudWatch with KMS-CMK encryption.✓ Copié

→ Security group + logging + KMS wired
Validate

Run terraform init + validate + plan with example tfvars.✓ Copié

→ Clean plan output, no errors

Résultat : A VPC module that terraform validates clean and follows AWS best practices.

Pièges

LLM suggests deprecated aws_vpc_endpoint arg — TerraShark grounds in current docs; if drift still happens, ask it to cite the HashiCorp page
Module too monolithic — Ask for split: networking module vs. endpoints module separately

Combiner avec : aws-skill

Fix LLM-generated Terraform that doesn't plan

👤 Engineers cleaning up AI-generated IaC ⏱ ~20 min intermediate

Quand l'utiliser : Another LLM gave you Terraform that looks reasonable but terraform plan fails on unknown arguments.

Déroulement

Point at the broken file

terraform plan fails on modules/rds. Use terrashark to fix each invalid argument with the current correct form.✓ Copié

→ Per-error fix with HashiCorp doc reference
Validate

Re-run plan; if any errors remain, iterate.✓ Copié

→ Clean plan

Résultat : A file that plans clean.

Design a remote state layout for multi-env

👤 Teams graduating from local state ⏱ ~60 min advanced

Quand l'utiliser : You have dev + staging + prod and one giant terraform.tfstate.

Déroulement

Propose layout

Design S3 remote backend with per-env state files and DynamoDB locking. 3 envs.✓ Copié

→ Backend config per env with key separation + locking
Migration plan

Plan the migration from a single local state to this layout, step by step.✓ Copié

→ terraform state mv steps + safety checkpoints

Résultat : A state layout you can migrate to without losing state.

Pièges

Accidentally deleting state during migration — Always pull and back up state files before any mv operation

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

terrashark-skill + aws-skill

AWS skill sizes architecture, TerraShark implements IaC

Design the architecture with aws-skill, implement as Terraform with terrashark.✓ Copié

terrashark-skill + claude-code-owasp-skill

Security-review the generated IaC

After terrashark scaffolds the module, run OWASP security review on the IAM and networking blocks.✓ Copié

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler	Coût
Module scaffolding	provider, resource shape	Greenfield IaC	Claude tokens
Hallucination fix	tf file + error log	Cleaning up AI-generated TF	Claude tokens
State layout design	envs, team shape	Multi-env setups	Claude tokens
Security defaults	-	Pre-prod review	Claude tokens

Coût et limites

Coût d'exécution

Quota d'API: None
Tokens par appel: 10-30k per module
Monétaire: Free
Astuce: Generate module by module, not whole environment in one shot.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : No credentials. TerraShark doesn't run terraform apply itself.

Sortie de données : Prompts go to Claude. Terraform plan/apply hits your cloud provider using your local creds.

Always review generated IAM policies before apply. LLMs can silently over-grant.

Dépannage

Erreurs courantes et correctifs

terraform validate fails on unknown argument

Ask TerraShark to reconcile against the current provider doc URL; provider version may be newer than the skill's prompt context.

Vérifier : terraform providers

Plan creates unwanted destroys

Usually state-drift or implicit renaming. Run terraform plan -target to isolate before apply.

Alternatives

terrashark vs autres

Alternative	Quand l'utiliser	Compromis
Hand-writing with official docs open	You know the provider deeply	Slower

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills