M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
T

TerraVision

Community
Automatically turn Terraform code into professional cloud architecture diagrams.
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #176 of 438
Stars
★ 1.7k Very popular
Transport
stdio (local process)
Runtime
Python 3.10+ · Prebuilt binary
Credentials
Optional API key
License
AGPL-3.0
Last commit
56FMRS · C

The supplied materials identify TerraVision as an AGPL-3.0 open-source, locally run Terraform diagram generator with stdio MCP startup support. It offers full AWS coverage and core-service support for Azure and GCP, but the materials do not provide MCP tool names or client compatibility information.

Strongest · Security and permissions 14/20 Weakest · Reliability 8/20

Reliability
8/20
Security and permissions
14/20
Maintenance
11/20
Documentation
13/20
Setup experience
10/20
Why each score
Reliability 8/20
The manifest gives a coherent PyPI/uvx/stdin-stdout startup path and identifies an MCP subcommand; the README confirms the intended MCP use case. However, no tool list, tool parameters, initialization/tool-list handshake evidence, MCP tests, or implementation-level error handling is provided, so actual handshake and behavior cannot be verified. The static calibration therefore requires a deduction.
Security and permissions 14/20
The README states that operation is client-side, requires no cloud access, and does not send Terraform source away; pre-generated plan mode also avoids cloud credentials. Optional Bedrock and restapi backends send metadata and a summary graph to external services and use AWS credentials or an API key, while MCP-specific permissions, confirmation, network scoping, and sensitive-data handling are not specified in the supplied material. This warrants a deduction, but no red-line risk is evidenced.
Maintenance 11/20
The project is not archived and has a clearly identified GitHub repository, AGPL-3.0 license, version 0.46.3, a lint-and-test CI badge, issue tracking, and contribution/documentation entry points. The supplied material does not verify release cadence, commit activity, dependency maintenance, a vulnerability-response process, or maintainer commitments, so the score is reduced.
Documentation 13/20
The README covers prerequisites, basic usage, Terraform plan inputs, output formats, cloud-provider coverage, AI backends, data boundaries, CI/CD, troubleshooting, and links to layered documentation, with several examples. It does not provide MCP tool names and parameters, mainstream-client connection configuration, a permission model, or clear limits and cost details; several relevant details are only linked externally. Full marks are therefore not justified.
Setup experience 10/20
The manifest provides a PyPI package, pinned version, uvx runtime hint, and stdio transport; the README lists Python 3.10+, Terraform, Graphviz, and Git prerequisites and gives CLI examples. It does not include a mainstream MCP client configuration example, and the dependency burden, MCP-specific connection steps, and platform-compatibility evidence are incomplete, making this a plausible but fairly manual setup.

Static review · not runListed 2026-08-14

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesRuns commands or codeUses the network

Best for

  • Developers and platform engineering teams using Terraform
  • Teams maintaining multi-cloud architecture documentation
  • Users who want local processing of infrastructure code

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

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

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

Setup

Before you start

Runtime：Python 3.10+ · Prebuilt binary

TV_RESTAPI_KEY optionalsecret Optional: API key (secret) for the restapi endpoint, only used with --ai-annotate restapi.
Other optional settings (2)
TV_RESTAPI_URL optional Optional: URL of an OpenAI-compatible annotation endpoint, only used with --ai-annotate restapi; see the Annotations Guide.
TV_RESTAPI_MODEL optional Optional: model name to use with the restapi endpoint, only used with --ai-annotate restapi.

Start it with uvx: uvx --from terravision[mcp] terravision mcp. The environment requires Python 3.10+; normal Terraform processing also requires Terraform 1.x, Graphviz, and Git.

Check that it works

Configure your client to run uvx --from terravision[mcp] terravision mcp, then ask the AI to diagram a Terraform directory; if the client invokes the server and produces architecture.png or an interactive HTML file, the install works.

Troubleshooting

  1. Confirm that Python 3.10 or newer is installed
  2. Confirm that Terraform 1.x, Graphviz, and Git are installed and available
  3. When using a pre-generated plan, provide both the plan JSON and graph DOT files
  4. Check the Terraform workspace, varfile, and source directory
  5. For AI annotations, verify the selected backend configuration and AWS credentials or REST API environment variables

Things to try

Once connected, you can ask your AI assistant things like:

  • Generate a cloud architecture diagram from my Terraform code in ./path-to-your-terraform
  • Draw the architecture for tests/fixtures/aws_terraform/eks_automode using official AWS icons and open it
  • Create an interactive HTML architecture diagram from https://github.com/patrickchugh/terraform-examples.git//aws/wordpress_fargate
  • Generate a simplified high-level diagram from this Terraform, without VPCs and subnets

Use cases

Generate architecture diagrams from Terraform infrastructure
Automatically update architecture documentation in CI/CD
Create interactive, offline HTML architecture diagrams
Export editable draw.io architecture files

Overview

TerraVision is a locally run MCP server that generates cloud architecture diagrams from Terraform code or pre-generated Terraform plans. It supports AWS, Google Cloud, and Azure, uses official cloud-service icon sets, and can produce interactive HTML, PNG, SVG, PDF, and editable draw.io outputs.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 63.3k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision f5d6b3ea92b2 Data synced 2026-10-19 Read the FMRS scoring method