tf-mcp-server

MCP server package intended to expose Terraform-related functionality to an AI agent via the Model Context Protocol (MCP). It acts as an adapter between agent tooling and Terraform workflows (e.g., inspecting/planning/applying), depending on the specific server implementation.

Evaluated Apr 04, 2026 (27d ago)
Homepage ↗ Infrastructure devtools infrastructure mcp terraform ai-agent-tools
⚙ Agent Friendliness
36
/ 100
Can an agent use this?
🔒 Security
41
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
40
Error Messages
0
Auth Simplicity
35
Rate Limits
0

🔒 Security

TLS Enforcement
70
Auth Strength
35
Scope Granularity
25
Dep. Hygiene
40
Secret Handling
35

Security cannot be fully assessed from the provided information. MCP servers that can run Terraform should use least-privilege credentials, avoid logging secrets, and implement strong guardrails against unintended apply/destroy operations. Rate limiting and detailed auth/authorization controls should be verified in the actual repo.

⚡ Reliability

Uptime/SLA
0
Version Stability
45
Breaking Changes
40
Error Recovery
30
AF Security Reliability

Best When

You want an MCP tool interface for Terraform tasks so an AI agent can reason and then trigger controlled Terraform operations in your environment.

Avoid When

You cannot provide safe execution controls (least-privilege credentials, environment separation, approval gates) for Terraform actions.

Use Cases

  • Allowing AI agents to interact with Terraform workflows through MCP tools
  • Automating Terraform plan review or policy checks with agent-driven tool calls
  • Generating Terraform-related answers/actions while keeping the agent within an MCP tool sandbox

Not For

  • Directly replacing Terraform CLI for all interactive use cases without agent orchestration
  • Security-critical unattended provisioning without additional guardrails/approvals
  • Production deployment automation without validating the underlying Terraform actions and permissions

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

OAuth: No Scopes: No

Authentication specifics are not provided in the supplied content. MCP servers that execute Terraform typically rely on local/agent-provided credentials (e.g., cloud provider credentials, Terraform backend auth), but this cannot be verified here.

Pricing

Free tier: No
Requires CC: No

No pricing information was supplied; as a package/repo, it is assumed to be self-hosted unless stated otherwise.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Terraform actions are not inherently safe/idempotent (especially apply); ensure the agent cannot run destructive actions without explicit approvals
  • Tool calls may depend on local filesystem/project context and credentials availability; agents can fail when required env/config is missing

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for tf-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered