← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionTerraform MCP ServerGenerate more accurate Terraform and automate workflows for HCP Terraform and Terraform Enterprise.GitHub MCP ServerGitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
FMRS65 / 100 · C76 / 100 · B
Reliability8 / 2013 / 20
Security and permissions14 / 2014 / 20
Maintenance14 / 2018 / 20
Documentation16 / 2017 / 20
Setup experience13 / 2014 / 20
Best for
  • Teams using HCP Terraform or Terraform Enterprise
  • Developers integrating Terraform into IDEs like VS Code and Cursor
  • DevOps engineers automating IaC workflows
  • Teams that want an AI assistant to directly operate on GitHub repos and collaboration workflows
  • Users already in the GitHub Copilot ecosystem who want a zero-deployment remote option
Not for
  • Not suitable for local-only Terraform use without HCP Terraform/Terraform Enterprise
  • Not for environments requiring complex custom instructions or high security without careful review
  • Scenarios where you don't want the assistant to have write access to repos (enable only read-only toolsets)
  • Environments with strict network isolation for private repos that can't reach the official remote endpoint
Required permissions
  • Requires Terraform API token (TFE_TOKEN) to access HCP Terraform or Terraform Enterprise
  • Runs in a Docker container, requiring network access
  • If ENABLE_TF_OPERATIONS is enabled, can execute Terraform operations, requiring explicit approval
  • A personal access token (PAT) or OAuth App token; effective scope depends on the token's own permissions
  • Enabling toolsets like actions/issues/pull_requests grants write access — request tokens on a least-privilege basis
Risks and side effects
  • Server may expose Terraform data to MCP client and LLM; avoid untrusted clients
  • Outputs are generated dynamically; review to align with security and cost policies
  • In streamable-http mode, TFE_ADDRESS cannot be set by clients to prevent redirect attacks
  • Shared secret (TF_MCP_SHARED_SECRET) should only be used over TLS
  • Write toolsets (creating/merging PRs, triggering workflows) can cause accidental changes if the token is overscoped — try a read-only toolset first
  • In hosted mode, credentials travel via the Authorization header — make sure the client-to-api.githubcopilot.com connection is trusted
Supported clientsClaude Desktop, Claude Code, VS Code, Cursor, Windsurf, JetBrains IDEs, Zed, Amp
Tools015