Excalidraw MCP Diagramming
Create and edit diagrams on a live Excalidraw canvas using the Excalidraw MCP server. Use when asked to draw, diagram, sketch, or visualise architectures, workflows, data flows, system designs, flowcharts, mind maps, or sequence diagrams. Trigger phrases include "create an excalidraw", "draw me a diagram", "make a flowchart", "visualise the system", "diagram this architecture", "export to PNG/SVG". Can export to PNG, SVG, .excalidraw file, or a shareable URL. Do NOT use for Draw.io or diagrams.net output (use drawio-mcp-diagramming instead).
Install
npx skills add thomast1906/github-copilot-agent-skills --skill excalidraw-mcp-diagramminggit clone --depth 1 https://github.com/thomast1906/github-copilot-agent-skills.git /tmp/github-copilot-agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/github-copilot-agent-skills/.github/skills/excalidraw-mcp-diagramming ~/.claude/skills/excalidraw-mcp-diagrammingPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Excalidraw MCP Diagramming
Create diagrams on a live Excalidraw canvas that renders in the browser and
updates in real time. You are not generating a static file — you are painting
onto a shared whiteboard through MCP tools. The canvas persists between calls,
so what you put on it in one call is visible in the next screenshot.
## When to Use
- The user asks to "create an excalidraw", "draw me a diagram", "make a flowchart", "visualise the system", or "diagram this architecture".
- The user wants an Excalidraw canvas output (not Draw.io / diagrams.net — use `drawio-mcp-diagramming` for that).
- The user wants to visualise an architecture, workflow, data flow, system design, mind map, or sequence diagram.
- The user asks to export a diagram to PNG, SVG, `.excalidraw` file, or a shareable URL.
- The user asks to update, change, or fix an existing Excalidraw diagram.
## Required MCP Server
The `excalidraw` MCP server must be present in `.vscode/mcp.json`:
```json
{
"servers": {
"excalidraw": {
"type": "http",
"url": "https://mcp.excalidraw.com"
}
}
}
```
If the MCP tools are not available, tell the user to add the server and reload
VS Code, then stop.
## Available Tools
**Essential — use on every diagram:**
| Tool | Purpose | When |
|---|---|---|
| `read_diagram_guide` | Returns server-side colour palette and sizing rules | First call — before any elements |Details
- Skill name
excalidraw-mcp-diagramming- Repository
- thomast1906/github-copilot-agent-skills
- Path
.github/skills/excalidraw-mcp-diagramming/SKILL.md- Repo updated
- 22 October 2026
FAQ
What does the Excalidraw MCP Diagramming skill do?
Create and edit diagrams on a live Excalidraw canvas using the Excalidraw MCP server. Use when asked to draw, diagram, sketch, or visualise architectures, workflows, data flows, system designs, flowcharts, mind maps, or sequence diagrams. Trigger phrases include "create an excalidraw", "draw me a diagram", "make a flowchart", "visualise the system", "diagram this architecture", "export to PNG/SVG". Can export to PNG, SVG, .excalidraw file, or a shareable URL. Do NOT use for Draw.io or diagrams.net output (use drawio-mcp-diagramming instead).
How do I install the Excalidraw MCP Diagramming skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add thomast1906/github-copilot-agent-skills --skill excalidraw-mcp-diagramming. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Excalidraw MCP Diagramming popular?
It lives in thomast1906/github-copilot-agent-skills, which has 206 GitHub stars and 54 forks.
Related skills
API Security Review
206thomast1906/github-copilot-agent-skills
Reviews Azure API Management configurations for security vulnerabilities, OWASP API Security Top 10 compliance, VNet Internal mode validation, Private Link verification, and Azure Security Benchmark alignment. Use when performing security audits, pre-deployment validation, or compliance reviews.
Apim Policy Authoring
206thomast1906/github-copilot-agent-skills
Creates production-ready Azure API Management policy XML for authentication (OAuth 2.0, JWT validation, subscription keys), rate limiting, CORS configuration, error handling, and API transformations. Use when implementing API security, access control, or request/response processing logic.
Apiops Deployment
206thomast1906/github-copilot-agent-skills
Guides deployment of Azure API Management infrastructure using Infrastructure as Code (Bicep/Terraform), CI/CD pipelines (GitHub Actions/Azure DevOps), and APIOps workflows. Use when deploying APIM, creating pipelines, or implementing dev→test→prod promotion strategies.
Import Model
213modular/skills
Use when importing a new model architecture into MAX from a Hugging Face model ID. Triggers on: "import a model into MAX", "add model to MAX", "bring up <HF model> in MAX". Workflow: inspect the Hugging Face config and modeling code, then scaffold from a similar ModuleV3 architecture. Implement each layer as a max.nn Module that matches HF, serve, then verify against the Hugging Face reference. When the server runs but output is wrong (gibberish, greedy mismatch, coherent-then-diverges), load debug-model for the divergence hunt.
Eval Model
213modular/skills
Measures the task accuracy of text models served by MAX using standard benchmarks such as GSM8K, MMLU, HellaSwag, ARC, AIME, GPQA, TruthfulQA, WinoGrande, and BABILong. Use when benchmarking a served model, comparing it with model-card or reference scores, verifying that a new MAX model produces correct answers, or running repeatable dataset evaluations against a MAX OpenAI-compatible endpoint.
Migrate Max V2 to V3
213modular/skills
Use when migrating a MAX model from the V2 graph API (max.nn.legacy, TensorValue, explicit Graph construction) to ModuleV3 (max.nn, Tensor, F.lazy() + compile()). Triggers on: "migrate to ModuleV3", "port a max.nn.legacy model to max.experimental", "convert TensorValue to Tensor", "update my model to the V3 API", "ModuleV3 migration". Workflow: read the concept map, rewrite imports and __call__ signatures, and replace graph building with compile(weights=...). Align weight names with the new module hierarchy and move the KV cache unflatten into forward(). Port sharding to a DeviceMesh when the
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.