M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

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

DimensionTerraVisionAutomatically turn Terraform code into professional cloud architecture diagrams.GitHub MCP ServerGitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
FMRS56 / 100 · C76 / 100 · B
Reliability8 / 2013 / 20
Security and permissions14 / 2014 / 20
Maintenance11 / 2018 / 20
Documentation13 / 2017 / 20
Setup experience10 / 2014 / 20
Best for
  • Developers and platform engineering teams using Terraform
  • Teams maintaining multi-cloud architecture documentation
  • Users who want local processing of infrastructure code
  • 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
  • Projects that do not use Terraform
  • Workloads requiring complete Azure or GCP resource coverage
  • Users seeking server-side cloud discovery or remote infrastructure management
  • 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
  • It needs to read local Terraform projects, variable files, and optionally plan JSON and graph DOT files
  • Normal operation requires local Terraform, Graphviz, and Git installations
  • AWS credentials are needed when using AWS Bedrock for AI annotations
  • 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
  • Azure and GCP currently have partial support limited to core services, so diagrams may be incomplete
  • When Bedrock or another REST API annotation backend is enabled, metadata and a summary graph are sent to the configured model service; the README states that .tf source files are not sent
  • Generated diagrams depend on the accuracy of the Terraform, plan, or graph inputs and do not replace infrastructure validation
  • 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