terrashark MCP — Use Cases, Install & Live Demo

Why use it

Key features

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

Live Demo

What it looks like in practice

terrashark-skill.replay ▶ ready

0/0

Install

Pick your 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
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

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

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

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

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

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

Add to context_servers. Zed hot-reloads on save.

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

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use terrashark

How to scaffold a production-grade AWS VPC module

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

When to use: Day one of a new AWS account; you want a VPC module that won't embarrass you in 6 months.

Prerequisites

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

Flow

Generate module

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

→ 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.✓ Copied

→ Security group + logging + KMS wired
Validate

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

→ Clean plan output, no errors

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

Pitfalls

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

Combine with: aws-skill

Fix LLM-generated Terraform that doesn't plan

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

When to use: Another LLM gave you Terraform that looks reasonable but terraform plan fails on unknown arguments.

Flow

Point at the broken file

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

→ Per-error fix with HashiCorp doc reference
Validate

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

→ Clean plan

Outcome: A file that plans clean.

Design a remote state layout for multi-env

👤 Teams graduating from local state ⏱ ~60 min advanced

When to use: You have dev + staging + prod and one giant terraform.tfstate.

Flow

Propose layout

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

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

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

→ terraform state mv steps + safety checkpoints

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

Pitfalls

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

Combinations

Pair with other MCPs for X10 leverage

terrashark-skill + aws-skill

AWS skill sizes architecture, TerraShark implements IaC

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

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.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
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

Cost & Limits

What this costs to run

API quota: None
Tokens per call: 10-30k per module
Monetary: Free
Tip: Generate module by module, not whole environment in one shot.

Security

Permissions, secrets, blast radius

Credential storage: No credentials. TerraShark doesn't run terraform apply itself.

Data egress: 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.

Troubleshooting

Common errors and fixes

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.

Verify: terraform providers

Plan creates unwanted destroys

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

Alternatives

terrashark vs others

Alternative	When to use it instead	Tradeoff
Hand-writing with official docs open	You know the provider deeply	Slower

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills