Skip to main content
Glama

Architecture Diagram MCP Server

arch-diagram-mcp is an MCP server that generates, reviews and imports cloud architecture diagrams for AWS, Azure and Google Cloud. It uses the official provider icons, about 1,800 in all, including Kubernetes, on-prem and SaaS services such as PostgreSQL, Redis, Kafka and Nginx. Diagrams render through Graphviz to PNG, self-contained SVG, PDF or JPG.

You can design new architectures, or diagram what already exists: from Terraform, or straight from a running Google Cloud project's own inventory, with the real resource names, however it was created.

Quick start. Install Graphviz, then add the server to your MCP client with any of these:

From

Command

PyPI, with uv

uvx arch-diagram-mcp

PyPI, with pipx

pipx install arch-diagram-mcp, then run arch-diagram-mcp

npm (launches the PyPI package through uv or pipx)

npx -y arch-diagram-mcp

For example, in Claude Code: claude mcp add architecture-diagrams -s user -- uvx arch-diagram-mcp. It is also listed in the MCP Registry as io.github.apatilgtn/architecture-diagrams.

Using it as a developer? Start with the developer guide. It covers connecting Claude Code, VS Code, Cursor or Claude Desktop, on your machine or to a shared team server, and gives example prompts. The rest of this README is for running and configuring the server.

Samples

These are the bundled templates and the Terraform example, rendered exactly as the server produces them. The score is from review_architecture. Click a diagram for the full-size image.

To regenerate them, run python scripts/render_samples.py.

The server has also been tested end to end on Google Cloud: a private bucket with signed URLs, and a private Cloud Run service with two layers of auth. See docs/CLOUD_TESTING.md for how it was tested, what was checked and the bug it found.

Related MCP server: aws-architecture-scanner

Tools

Tool

What it does

search_icons(query, provider?, limit?)

Ranked icon search by service name or alias (ecs, s3, aks, cloud run, redis)

list_icon_categories(provider)

Lists every category and service for a provider

list_templates(provider?) / get_template(id)

Returns bundled reference architectures as editable specs

validate_diagram(spec)

Checks a spec without rendering: icon ids (with suggestions), references, nesting cycles, limits

generate_architecture_diagram(spec)

Renders the diagram; returns file paths, a JSON summary and an inline PNG preview

review_architecture(spec)

Runs a heuristic Well-Architected review and returns a 0–100 score, a grade and findings with recommendations

diagram_from_terraform(title, terraform_json | path, ...)

Builds a diagram from terraform show -json output (plan or state) or a raw .tfstate file

diagram_from_inventory(title, inventory_json | path, projects?, regions?, labels?, ...)

Builds a diagram of resources already running in Google Cloud from a Cloud Asset Inventory export, with real names

server_info()

Reports the version, Graphviz status, icon count, output directory and limits

There is also one prompt, design_architecture(provider, workload, requirements). It walks the model through choosing a template, searching icons, validating, rendering and reviewing.

Bundled templates

  • aws_three_tier

  • aws_serverless_event_driven

  • azure_webapp_hub_spoke

  • azure_aks_microservices

  • gcp_serverless_data

  • gcp_gke_microservices

Every template is tested to validate, to render, and to have no critical- or high-severity review findings.

Diagram spec

{
  "title": "My App",
  "direction": "LR",
  "theme": "light",
  "output_formats": ["png", "svg"],
  "clusters": [{"id": "vpc", "label": "VPC 10.0.0.0/16"}, {"id": "app", "label": "Private subnet", "parent": "vpc"}],
  "nodes": [{"id": "api", "type": "aws.compute.ECS", "label": "orders-api", "cluster": "app"}],
  "edges": [{"source": "alb", "target": "api", "label": "HTTPS", "style": "dashed"}]
}

Review rules

Pillar

Rules

Security

Internet → data store (critical); internet → compute without a gateway (high); no WAF; no secrets/KMS; no identity provider; data stores outside a network boundary; no egress control

Reliability

VM without a load balancer; single region; no backup; deep synchronous call chains

Operational Excellence

No monitoring; no CI/CD; unconnected components

Performance Efficiency

No CDN for public traffic; no cache layer

The rules only see what the diagram shows. Treat findings as review prompts, not proof of a misconfiguration.

Terraform import

terraform show -json plan.out > plan.json gives the best result, because the plan includes the configuration's references.

  • Mapped resources: about 140 AWS, Azure and GCP resource types become nodes.

  • Boundaries: VPC/VNet, subnet, resource group and Container Apps environment resources become nested clusters. Nodes are placed in the most specific boundary they reference, either directly or through a NIC.

  • Edges: references between resources become edges, and module outputs are resolved.

  • Inferred edges: links that pass through plumbing resources become dashed edges, oriented edge → compute → messaging → data. Plumbing resources include listeners, target groups, NICs, role assignments, Front Door origins and backend services.

  • Unmapped types: the result lists them, so you can see what was left out.

Inventory import (Google Cloud)

For infrastructure that is already running, however it was created (console, gcloud, scripts, Terraform, Pulumi), export the project's inventory and pass it to diagram_from_inventory:

gcloud asset list --project <project-id> --content-type resource \
  --asset-types "$(arch-diagram-mcp --gcp-asset-types)" --format json > assets.json

--gcp-asset-types prints the 54 asset types the importer uses. Asking only for those keeps the export small: a test project went from 4.4 MB to 535 KB with the same diagram. The caller needs roles/cloudasset.viewer and the Cloud Asset API enabled.

  • Names: every node keeps its real name. A second line adds detail, such as the database version, machine type, ingress setting, replica count or cron schedule.

  • Boundaries: Project › VPC › Subnet › GKE cluster › Namespace. Shared VPC networks owned by another project are drawn under that project. Cloud Run with direct VPC egress sits in its subnet.

  • Edges from configuration:

    • Cloud SQL, secret, KMS, Pub/Sub, bucket and Redis references in annotations and environment variables;

    • URLs matched to the Cloud Run service or function that owns them (push subscriptions, Scheduler targets, env vars);

    • the load balancer chain (forwarding rule › proxy › URL map › backend › NEG, bucket or MIG), with path rules, CDN and Cloud Armor;

    • Eventarc triggers, dead-letter topics, BigQuery and Cloud Storage subscriptions, VPC connectors.

  • Noise left out: GKE system namespaces and nodes, MIG member VMs (drawn as one MIG), Cloud Functions' own Run services, build and staging buckets, routes, firewalls and RBAC objects.

  • Filters: projects and regions are hard limits. labels (for example {"app": "payments"}) selects resources plus the ones they connect to (include_neighbors, on by default).

  • Limits: calls that exist only in application code can't be seen. The result returns the spec, so you can add those edges and re-render. External hosts found in env vars are listed in external_hosts.

Accepted formats: gcloud asset list JSON (recommended), gcloud asset export newline-delimited JSON, and gcloud asset search-all-resources --read-mask='*' JSON. Azure Resource Graph and AWS inventories are planned.

Install

Requires Python 3.11+ and Graphviz.

winget install Graphviz.Graphviz        # Linux: apt install graphviz   macOS: brew install graphviz
python -m venv .venv
.venv\Scripts\python -m pip install -e ".[dev]"
.venv\Scripts\python -m pytest            # 85 tests

Register with Claude Code (stdio)

claude mcp add architecture-diagrams -s user `
  -e ARCH_DIAGRAM_OUTPUT_DIR=C:\Devops-Projects\Architecture-diagram-mcp\output `
  -- C:\Devops-Projects\Architecture-diagram-mcp\.venv\Scripts\python.exe -m arch_diagram_mcp

Run as a shared HTTP service

docker build -t arch-diagram-mcp:1.2.0 .
docker run -d -p 8000:8000 -v diagrams:/data \
  -e ARCH_DIAGRAM_AUTH_TOKENS="ci=$(openssl rand -hex 32),platform-team=$(openssl rand -hex 32)" \
  -e ARCH_DIAGRAM_PUBLIC_BASE_URL=https://diagrams.internal.example.com \
  -e ARCH_DIAGRAM_URL_SIGNING_KEY=$(openssl rand -hex 32) \
  -e ARCH_DIAGRAM_ALLOWED_HOSTS="diagrams.internal.example.com:*" \
  arch-diagram-mcp:1.2.0

Clients connect to https://<host>/mcp with Authorization: Bearer <token>. GET /healthz is unauthenticated and works as a probe. The server runs stateless, so it scales horizontally behind a load balancer. All replicas must share ARCH_DIAGRAM_URL_SIGNING_KEY so any replica can serve any link.

Authentication

Mode

Set

Identity in audit logs

Roles

token

ARCH_DIAGRAM_AUTH_TOKENS="name=secret,..."

the token's name

Full access

oidc

ARCH_DIAGRAM_OIDC_ISSUER + ARCH_DIAGRAM_OIDC_AUDIENCE

preferred_username / upn / email, keyed by oid/sub

ARCH_DIAGRAM_READER_ROLE, ARCH_DIAGRAM_AUTHOR_ROLE

Token mode. Several named tokens can be active at once. To rotate, add the new token, roll out clients, then remove the old one. Each token must be at least 16 characters.

OIDC mode. The server validates JWTs against the issuer's published signing keys (JWKS, found by discovery or set with ARCH_DIAGRAM_OIDC_JWKS_URI). It checks:

  • signature (asymmetric algorithms only: no HS*, no none);

  • iss and aud;

  • exp and nbf, with 60 s leeway;

  • optional ARCH_DIAGRAM_OIDC_REQUIRED_SCOPES.

Roles come from the roles claim (Entra app roles) and the scp scope claim:

  • Reader: search, templates, validate, review.

  • Author: also render, and import Terraform or cloud inventories. Author implies Reader.

  • If neither role variable is set, any valid token gets full access.

The server publishes RFC 9728 metadata at /.well-known/oauth-protected-resource, and every 401 response points to it, so MCP clients can discover the authorization server.

Entra ID example:

  1. Register an API app with Application ID URI api://arch-diagrams.

  2. Set accessTokenAcceptedVersion: 2 in its manifest.

  3. Add app roles Diagrams.Reader and Diagrams.Author, and assign them to groups.

  4. Configure the server:

ARCH_DIAGRAM_OIDC_ISSUER=https://login.microsoftonline.com/<tenant-id>/v2.0
ARCH_DIAGRAM_OIDC_AUDIENCE=api://arch-diagrams      # v2 tokens may carry the app's client id instead; list both
ARCH_DIAGRAM_READER_ROLE=Diagrams.Reader
ARCH_DIAGRAM_AUTHOR_ROLE=Diagrams.Author

Entra ID has no dynamic client registration. Clients either use a pre-registered client app, or pass a token they already hold, e.g. az account get-access-token --resource api://arch-diagrams.

Artifact storage

Over HTTP, responses contain download URLs instead of server file paths:

ARCH_DIAGRAM_STORAGE

Links

Credentials

local (default)

https://<PUBLIC_BASE_URL>/artifacts/<file>?exp=..&sig=.., served by this server and HMAC-signed

ARCH_DIAGRAM_URL_SIGNING_KEY

s3

SigV4 presigned GET; objects encrypted with SSE-S3, or SSE-KMS when ARCH_DIAGRAM_S3_KMS_KEY_ID is set

Standard AWS chain (IRSA, instance role, env, profile)

azure

Read-only, HTTPS-only SAS. Uses a user-delegation key via Entra ID with ARCH_DIAGRAM_AZURE_ACCOUNT_URL, or an account key via AZURE_STORAGE_CONNECTION_STRING

Managed / workload identity needs Storage Blob Data Contributor

gcs

V4 signed URL. Signs locally with a service-account key, or through IAM signBlob under workload identity

Needs Storage Object Creator and Service Account Token Creator

  • Object keys: <prefix>/<yyyy>/<mm>/<dd>/<sha256(caller)[:16]>/<file>. Files are separated per caller, and keys never contain user names.

  • Link lifetime: set by ARCH_DIAGRAM_URL_TTL_S, default 1 h, maximum 7 days.

  • Cleanup: ARCH_DIAGRAM_DELETE_LOCAL_AFTER_UPLOAD=true removes local copies once a cloud upload succeeds. For cloud objects, use a bucket lifecycle rule.

  • Served SVGs: sent with Content-Security-Policy: sandbox and nosniff.

  • Terraform paths: diagram_from_terraform(path=...) is disabled over HTTP, so remote callers can't read server files.

Configuration (environment)

Variable

Default

Purpose

ARCH_DIAGRAM_OUTPUT_DIR

~/architecture-diagrams

Where diagrams are written

ARCH_DIAGRAM_INPUT_ROOTS

cwd + output dir

os.pathsep-separated directories that diagram_from_terraform(path=...) may read

ARCH_DIAGRAM_MAX_NODES / _MAX_EDGES / _MAX_CLUSTERS

300 / 800 / 100

Spec size limits

ARCH_DIAGRAM_RENDER_TIMEOUT_S

60

Graphviz is killed after this many seconds

ARCH_DIAGRAM_MAX_TERRAFORM_BYTES

25 MB

Terraform input size limit

ARCH_DIAGRAM_RETENTION_DAYS

0 (keep forever)

Deletes generated files older than N days

ARCH_DIAGRAM_KEEP_DOT_SOURCE

true

Keeps the .dot file for hand-editing

ARCH_DIAGRAM_INLINE_PNG_MAX_BYTES

4 MB

Larger PNGs are returned as a path only

ARCH_DIAGRAM_FONT

auto

Font family; auto picks Segoe UI on Windows, Helvetica Neue on macOS, DejaVu Sans on Linux

ARCH_DIAGRAM_PNG_DPI

144

PNG/JPG resolution (72–300)

ARCH_DIAGRAM_LOG_LEVEL

INFO

JSON logs go to stderr, one audit line per tool call

ARCH_DIAGRAM_HTTP_HOST / _HTTP_PORT

127.0.0.1 / 8000

HTTP bind address and port

ARCH_DIAGRAM_AUTH_MODE

auto

none / token / oidc; inferred from the variables below

ARCH_DIAGRAM_AUTH_TOKENS

–

name=secret,... named bearer tokens (the legacy single ARCH_DIAGRAM_AUTH_TOKEN still works)

ARCH_DIAGRAM_OIDC_ISSUER / _OIDC_AUDIENCE / _OIDC_JWKS_URI / _OIDC_REQUIRED_SCOPES

–

OIDC validation

ARCH_DIAGRAM_READER_ROLE / _AUTHOR_ROLE

–

Role names for RBAC (OIDC)

ARCH_DIAGRAM_PUBLIC_BASE_URL

–

External URL; used for download links and OAuth metadata

ARCH_DIAGRAM_STORAGE

local

local / s3 / azure / gcs

ARCH_DIAGRAM_STORAGE_BUCKET / _STORAGE_PREFIX

– / diagrams/

Bucket or container, and key prefix

ARCH_DIAGRAM_S3_REGION / _S3_KMS_KEY_ID / _AZURE_ACCOUNT_URL

–

Backend specifics

ARCH_DIAGRAM_URL_TTL_S

3600

Download-link lifetime (60 s – 7 days)

ARCH_DIAGRAM_URL_SIGNING_KEY

random per process

HMAC key for local links; ≥32 chars; share it across replicas

ARCH_DIAGRAM_DELETE_LOCAL_AFTER_UPLOAD

false

Removes local files after a cloud upload

ARCH_DIAGRAM_ALLOWED_HOSTS / _ALLOWED_ORIGINS

–

Comma-separated Host/Origin allow-lists (DNS-rebinding protection)

ARCH_DIAGRAM_ALLOW_UNAUTHENTICATED

false

Allows a non-loopback bind without a token (only behind an authenticating proxy)

Security model

  • Spec validation: ids, colours and styles are pattern-checked, and size limits apply.

  • Text escaping: titles, node labels and cluster labels are always written as literal strings, never as Graphviz HTML labels. Edge labels are HTML-escaped. A label therefore can't inject DOT statements, such as an image= attribute that reads local files.

  • Rendering: Graphviz runs as a subprocess with a hard timeout, and partial output is deleted on failure.

  • Output files: file names are sanitised, timestamped and uniquely suffixed. Retention cleanup only touches files the server generated.

  • Terraform input: file reads are confined to ARCH_DIAGRAM_INPUT_ROOTS and size-limited.

  • HTTP:

    • Static tokens are compared in constant time against every configured token.

    • OIDC JWTs are fully validated, and key-confusion and alg: none tokens are rejected (both are tested).

    • Per-tool RBAC applies, and every audit line records the caller.

    • The server refuses to bind to a public address without authentication.

    • DNS-rebinding protection uses Host/Origin allow-lists.

    • The container runs as a non-root user.

  • SVG output: icons are embedded, so the files don't leak local paths and render anywhere.

Layout

src/arch_diagram_mcp/
  server.py        MCP tools, prompt, error mapping, audit logging
  catalog.py       icon index, alias resolution, ranked search, suggestions
  models.py        spec schema + semantic validation
  renderer.py      Graphviz source build, timed subprocess render, themes, SVG inlining, retention
  review.py        Well-Architected heuristic rules and scoring
  terraform.py     Terraform plan/state -> spec
  gcp_inventory.py Cloud Asset Inventory export of running GCP resources -> spec
  template_library.py + templates/*.json   reference architectures
  auth.py          principals, static-token + OIDC authenticators, RBAC
  storage.py       local signed links, S3 / Azure Blob / GCS uploads with signed URLs
  http_app.py      streamable-HTTP app, auth middleware, OAuth resource metadata, /artifacts, /healthz
  config.py, logs.py, __main__.py
tests/             85 tests: catalog, validation, rendering, label injection, review, Terraform, GCP
                   inventory (real export fixture), MCP tools, HTTP auth, OIDC (incl. attack tokens), RBAC,
                   signed links, S3 (moto), Azure SAS, GCS V4
docs/USER_GUIDE.md      developer guide: connecting clients, example prompts, troubleshooting
docs/CLOUD_TESTING.md   how the server was tested on real Google Cloud
docs/samples/      rendered sample diagrams shown above
scripts/render_samples.py   regenerates docs/samples/
scripts/e2e_cloud.py, run_impersonated.py   real-cloud end-to-end test tools

License

Apache-2.0. The bundled provider icons come from the diagrams library and remain subject to their owners' terms.

Available Tools

10 tools
diagram_from_inventoryA

Diagram infrastructure that is already running, from the cloud's own inventory, with real names.

Google Cloud: pass the output of gcloud asset list --project <id> --content-type resource --format json (or gcloud asset export newline-delimited JSON) in inventory_json, or a file path inside the configured input roots. Works however the resources were created (console, gcloud, IaC).

Layout: Project > VPC > Subnet > GKE cluster > namespace. Edges come from configuration (Cloud SQL/secret/Pub/Sub references, URLs matched to Cloud Run services, load balancer backends, push subscriptions, Scheduler targets, VPC connectors). Filter with projects, regions and labels (e.g. {"app": "payments"}); include_neighbors keeps resources that matched resources connect to. Calls made only in application code are not visible: add those edges to the returned spec and re-render with generate_architecture_diagram.

Inputs: title (required), path, labels, regions, +8 more.

diagram_from_terraformA

Build a diagram from Terraform: terraform show -json plan.out, state JSON, or a .tfstate file.

Pass the JSON text in terraform_json, or a file path inside the configured input roots. VPC/VNet/subnet/resource-group become nested boundaries; references become edges (dashed = inferred through listeners, NICs, role assignments, etc.). Returns the generated spec so it can be refined and re-rendered.

Inputs: title (required), path, direction, output_formats, +2 more.

generate_architecture_diagramA

Render an architecture diagram with official provider icons.

spec.nodes: services (type = icon id from search_icons). spec.clusters: boundaries (account, subscription, project, region, VPC/VNet, subnet, AZ, namespace), nested with parent. spec.edges: node-to-node connections with optional label, colour and style. spec.output_formats: any of png, svg (self-contained), pdf, jpg. Returns file paths and an inline PNG preview.

Inputs: spec (required).

get_templateA
Read-onlyIdempotent

Return a reference architecture spec to customise and pass to generate_architecture_diagram.

Inputs: template_id (required). Returns: object

list_icon_categoriesA
Read-onlyIdempotent

List every category of a provider and the service icons in each.

Inputs: provider (required). Returns: object

list_templatesB
Read-onlyIdempotent

List bundled reference architectures (AWS, Azure, GCP) that can be loaded with get_template.

Inputs: provider. Returns: result

review_architectureA
Read-onlyIdempotent

Heuristic Well-Architected review of a spec (security, reliability, operations, performance).

Returns a 0-100 score, grade, and findings with recommendations. Findings reflect only what the diagram shows.

Inputs: spec (required). Returns: object

search_iconsB
Read-onlyIdempotent

Search ~1,900 official icons by service name, alias or category.

Examples: 'ecs', 's3', 'aks', 'cloud run', 'postgres', 'redis', 'kafka', 'load balancer'. Returns canonical ids (usable as node type) and their aliases.

Inputs: query (required), limit, provider. Returns: result

server_infoA
Read-onlyIdempotent

Report version, Graphviz status, icon count, storage, auth mode, caller identity and limits.

Inputs: no named parameters. Returns: object

validate_diagramA
Read-onlyIdempotent

Check a spec without rendering: icon ids (with suggestions), references, nesting, limits.

Inputs: spec (required). Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 10 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: rendering (generate_architecture_diagram), discovery (search_icons, list_icon_categories, list_templates, get_template), validation (validate_diagram vs review_architecture), and import (diagram_from_terraform vs diagram_from_inventory). Minor overlap between search_icons and list_icon_categories (both surface icons) and between validate_diagram and review_architecture (both inspect a spec), but descriptions clarify the intent difference.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (search_icons, list_templates, get_template, validate_diagram, review_architecture) and the two import tools consistently use diagram_from_<source>. Deviations exist: server_info is noun-only and generate_architecture_diagram is a longer verb phrase, but the set reads predictably overall.

    Tool Count5/5

    Ten tools is well-scoped for a diagram generation server, covering rendering, discovery, templates, validation, review, and two import sources without redundancy. Each tool earns its place in the workflow.

    Completeness4/5

    The surface covers the full diagram lifecycle: discover icons, load templates, generate, validate, review, and import from Terraform/inventory. Minor gaps remain—no explicit tool to save/manage custom templates or to retrieve/edit previously generated diagram files—but core workflows are well supported.

    Related MCP Connectors

    Related MCP Servers