The best MCP servers for Terraform — give AI agents provider documentation, module search, and plan/state context for infrastructure as code.
Why it’s hereMost popular in this category on AllMCPs
The official Terraform MCP Server seamlessly integrates with the Terraform ecosystem, enabling provider discovery, module analysis, and direct Registry API integration for advanced Infrastructure as Code workflows.
Why it’s hereCommunity pick
AI-native architecture platform for engineering teams. Describe a system in natural language (e.g. "payment service with Stripe, Kafka, PostgreSQL") → get an interactive typed diagram with 167 cloud components → export to 14 production frameworks (Java Spring Boot, Python FastAPI, Go chi, Rust Axum, .NET, Kotlin Ktor, Ruby Rails, Elixir Phoenix, Docker Compose, Terraform, Mermaid, ADR, and more). Drift detection (syncarchitecture) scores saved diagrams against live code 0–100 with a structured diff. 9 quality-lint rules catch orphans, SPOFs, god services. Also includes a secondary persistent code-graph layer for AI coding agents (free offline via npx tentra-mcp --local init). Agent-as-LLM pattern — zero LLM cost on our side, zero API key on yours. 35 MCP tools. Works in Cursor, Claude Code, Codex, Windsurf.
Why it’s hereCommunity pick
Oracle Cloud discovery + Terraform generation for AI agents — read-only, secret-safe.
Why it’s hereCommunity pick
Open-source AWS security scanner with attack chain detection, breach cost estimation, and copy-paste remediation (CLI + Terraform). 47 checks, 16 attack chain rules. First free standalone AWS security MCP server.
Why it’s hereCommunity pick
Safety-first Terraform operations: plan/apply/destroy with two-step confirmation gates, plan risk & cost analysis that flags expensive always-on resources (NAT gateways, EKS, Azure Firewall), drift detection, import/taint/refresh, provider auth pre-flight checks, and audit logging.
Why it’s hereCommunity pick
Natural-language cloud architecture intelligence for AWS, GCP, Azure, and Databricks. 19 tools for architecture design, cost estimation, compliance validation (HIPAA, SOC 2, FedRAMP, GDPR, PCI-DSS, Well-Architected), security scanning, Terraform/CloudFormation export, and blast-radius analysis.
Why it’s hereCommunity pick
Visualise diagrams, generate Terraform HCL, and manage Azure/AWS/GCP infrastructure with AI.
Why it’s hereCommunity pick
Fail-closed policy guardrails for AI agents running kubectl, terraform, helm, and argocd.
The safest Terraform servers give the agent documentation and registry lookups so it writes correct HCL, while you keep running plan and apply yourself. Servers that run apply let an agent change real infrastructure, so gate them behind manual approval.
This page ranks Terraform MCP servers by real usage across the AllMCPs directory. Registry and documentation servers are the most common and lowest-risk starting point.
Only with manual approval. Let the agent write HCL and read plan output, and keep the apply step with a human or a CI pipeline that requires review.
Documentation and registry servers need none. Servers that run plan or read state need the same provider credentials Terraform itself uses.