Tfmcp
Unclaimed🌍 Terraform Model Context Protocol (MCP) Tool - An experimental CLI tool that enables AI assistants to manage and operate Terraform environments. Supports reading Terraform configurations, analyzing plans, applying configurations, and managing state with Claude Desktop integration. ⚡️
Install
docker run -it tfmcpSet up this server
More in AI & ML
Browse the full directoryUnclaimed listing
Is this your MCP server?
This listing was auto-indexed from the public record. Claim it to edit the page, set compatibility and unlock growth tools. Takes under two minutes.
Claim this serverSecurity profile
Claimed and verified servers get a weekly static scan that shows what the code can reach: external services, environment variables, shell commands, agent configuration folders, plus any dependencies with known advisories. Claim this listing to get one. How the security profile works
40 of 40 tools
Documented tools (40)
From project documentation. A server handshake does not verify each tool’s description or behavior.
analyze_module_health
Module health with cohesion/coupling metrics
analyze_plan
NEW Analyze plan with risk scoring and recommendations
analyze_state
NEW Analyze state with drift detection
analyze_terraform
Analyze configuration
apply_terraform
Apply Terraform configuration
check_provider_lockfile
Check .terraform.lock.hcl for reproducible provider selections
destroy_terraform
Destroy Terraform-managed infrastructure
detect_drift_candidates
Detect drift candidates from readable state without modifying infrastructure
detect_terraform_entrypoints
Detect likely root module entrypoints
get_provider_capabilities
Provider resources, data sources, functions, and guides
get_provider_details
Provider details (HashiCorp-compatible alias)
get_provider_docs
Provider documentation
get_provider_info
Provider details
get_resource_dependency_graph
Resource dependencies visualization
get_security_status
Security scan with secret detection
get_terraform_plan
Generate and show execution plan
get_terraform_state
Show current state
init_terraform
Initialize Terraform working directory
inspect_state_safety
Inspect state readability, drift risk, lockfile status, and blockers
inspect_terraform_project
Inspect local Terraform directories, modules, and likely entrypoints
list_terraform_resources
List all managed resources
prepare_terraform_change
Generate blockers, warnings, and a recommended change sequence
review_terraform_plan
Review plan risk, blockers, destructive changes, and recommendations
run_terraform_quality_checks
Run CI-friendly validation, module health, guideline, and lockfile checks
search_modules
Search modules (HashiCorp-compatible alias)
search_providers
Search providers (HashiCorp-compatible alias)
search_terraform_providers
Search providers
set_terraform_directory
Change active project directory
suggest_module_refactoring
Refactoring suggestions
summarize_plan_for_pr
Generate markdown plan summary for PR comments
terraform_fmt
NEW Format code
terraform_graph
NEW Generate dependency graph
terraform_import
NEW Import existing resources
terraform_output
NEW Get output values
terraform_providers
NEW Get provider info with lock file
terraform_refresh
NEW Refresh state
terraform_taint
NEW Taint/untaint resources
terraform_workspace
NEW Manage workspaces (list, show, new, select, delete)
validate_terraform
Validate configuration syntax
validate_terraform_detailed
Detailed validation with guidelines
Tool change history
FAQ
Questions about Tf MCP Server
- How do I connect Tf MCP Server to Claude?
- The listing records `docker run -it tfmcp` as its setup step. Run it, then follow the repository's instructions for the client configuration; the listing names Claude Desktop as compatible clients.
- Is Tf MCP Server free?
- The listed licence is MIT. Check the upstream terms for permitted use and commercial requirements; a public repository does not by itself mean the software is free or open source. Connected APIs and hosted services may have separate charges.
- What can Tf MCP Server do?
- Tf MCP Server documents 40 tools to the agent, including analyze_module_health, analyze_plan, analyze_state. The descriptions above come from project documentation. A live handshake does not test individual tool behavior.