Supports including Dynatrace as a component in architecture diagrams.
Allows generation of Excalidraw diagrams from structured node/edge definitions or Mermaid syntax.
Supports including Kong API gateway as a component in architecture diagrams.
Allows conversion of Mermaid diagram syntax into Excalidraw format.
Supports including OpenTelemetry as a component in architecture diagrams.
Supports including PostgreSQL database as a component in architecture diagrams.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@arch7 create a diagram for GKE cluster with Kafka and PostgreSQL"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Architecture diagram generator for Excalidraw, exposed as an MCP server.
Fork of excalidraw-architect-mcp by Bhukya Venkatesh (MIT License).
Cylinder shapes: vertical (databases), horizontal flattened (topics/queues)
60+ components with auto-styling: GCP (GKE, Cloud Run, GCS, BigQuery, Pub/Sub, VPC, PSC), Kong, Confluent (Kafka, Schema Registry, ksqlDB), Dynatrace, OpenTelemetry, AI/Agentic (LLM, Agent, MCP, Vector DB, RAG)
Smaller diamonds for agent nodes
Repackaged as arch7_mcp
Related MCP server: GCP Diagram MCP Server
pip install -e .Add to ~/.claude/settings.json:
{
"mcpServers": {
"arch7": {
"command": "python",
"args": ["-m", "arch7_mcp"]
}
}
}Tool | Description |
| Structured nodes/connections → .excalidraw |
| Mermaid syntax → .excalidraw |
| Add/remove/update nodes on existing file |
| Read diagram state for iteration |
from arch7_mcp.core.models import Node, Edge, DiagramGraph, Direction
from arch7_mcp.engine.layout import compute_layout
from arch7_mcp.engine.renderer import build_excalidraw_file, save_excalidraw
nodes = [
Node(id="gke", label="GKE Cluster", component_type="gke"),
Node(id="kafka", label="Kafka Topics", component_type="kafka"),
Node(id="pg", label="PostgreSQL", component_type="postgresql"),
]
edges = [
Edge(from_id="gke", to_id="kafka"),
Edge(from_id="kafka", to_id="pg"),
]
graph = DiagramGraph(nodes=nodes, edges=edges, direction=Direction.LEFT_RIGHT)
layout = compute_layout(graph)
doc = build_excalidraw_file(layout)
save_excalidraw(doc, "arch.excalidraw")MIT — see LICENSE. Original copyright Bhukya Venkatesh.
Create a new Excalidraw diagram from structured node and connection data.
The LLM provides a relationship map - this tool handles layout, styling, and rendering. No need to specify coordinates.
Inputs: nodes (required), connections (required), output_path (required), direction, +2 more. Returns: result
Get a structured summary of an existing Excalidraw diagram.
Call this BEFORE modify_diagram to understand what nodes and connections currently exist. The summary includes node ids, labels, component types, and the full connection topology.
Inputs: file_path (required). Returns: result
Convert Mermaid flowchart syntax into an Excalidraw diagram.
Supports the mermaid flowchart subset that AI agents commonly generate:
Directions: graph TD, LR, BT, RL
Node shapes: [text], {text}, ((text)), ([text])
Edge types: -->, ---, -.-> ==> with |label|
Subgraphs: subgraph Title ... end
Component types are auto-detected from node labels (e.g., a node labeled "PostgreSQL DB" automatically gets database styling).
Inputs: mermaid_syntax (required), output_path (required), theme. Returns: result
Modify an existing Excalidraw diagram created by this tool.
Supports iterative editing: add components, remove nodes, update labels, and rewire connections - without recreating the entire diagram.
IMPORTANT: Call get_diagram_info first to understand the current diagram state before making modifications.
Inputs: file_path (required), operations (required), theme. Returns: result
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 4 tools
Each tool has a clear, distinct role: creating a new diagram, retrieving diagram info, converting mermaid syntax, and modifying an existing diagram. No overlap in functionality.
Three tools follow a consistent verb_noun pattern (create_diagram, get_diagram_info, modify_diagram), while mermaid_to_excalidraw breaks the pattern but remains clear and predictable given its conversion purpose.
Four tools is a well-scoped number for a diagramming server, covering the essential operations (create, read, update, plus conversion) without being too few or excessive.
The tool set covers core create, read, and modify operations, with conversion support. A full delete diagram tool is missing, but modify_diagram allows node removal, so the gap is minor.
Create and manage Mermaid.js flowcharts and diagrams with AI agents via MCP.
Render, verify, describe, and safely edit Mermaid diagrams through MCP.
Generate cloud architecture diagrams, flowcharts, and sequence diagrams.
Create and edit architecture diagrams from your AI agent; get an SVG and a live editable canvas.
