---
title: "penecho-cloud"
description: "Create editable diagrams and interactive previews in a browser Canvas. Start as a guest, then sign in for Cloud saving and PenEcho Agent."
canonical: https://agentpluginsdirectory.com/plugins/penecho-cloud
last-updated: 2026-09-28
---

# penecho-cloud
Create editable diagrams and interactive previews in a browser Canvas. Start as a guest, then sign in for Cloud saving and PenEcho Agent.
- Slug: penecho-cloud
- Publisher: PenEcho
- Repository: https://github.com/penecho/penecho
- Manifest: integrations/penecho-cloud/plugin.json
- Version: 1.1.0
- License: MIT
- Category (editorial): other
- Skills: 1 (penecho-canvas)
- MCP servers: 1 (penecho-cloud)
- Stars: 2418
- Repository created: 2026-07-14
- Repository last pushed: 2026-09-27
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/penecho-cloud
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What penecho-cloud does, in the publisher's words

Create an architecture diagram or interactive preview with your AI assistant, mark up the result by hand, and ask the assistant to revise it on the same Canvas.

- Sign in at https://penecho.ai and open a Canvas.
- Enable Settings → MCP → Cloud MCP, or use Open MCP Canvas from the Dashboard MCP page. Keep the Canvas open in your browser.
- Install this plugin in a supported client and complete PenEcho OAuth authorization.
- Ask the assistant to list available PenEcho canvases, then create or revise content in the one you select.

The remote endpoint is https://penecho.ai/mcp (Streamable HTTP). OAuth uses authorization code with PKCE S256 and dynamic client registration. No shared API key is bundled. A PenEcho account is required. Canvas operations through MCP are free and use no PenEcho credits; your assistant's model provider may charge for model usage separately.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/penecho/penecho/HEAD/integrations/penecho-cloud/README.md

## Skills

- penecho-canvas: Create diagrams, interactive previews, and visual explanations on PenEcho Cloud canvases, or revise existing work from the user's handwriting and annotations.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- penecho-cloud: transport: stdio; command: npx -y mcp-remote@0.1.38 https://penecho.ai/mcp --transport http-only --resource https://penecho.ai/mcp

Read from the plugin's own mcp.json. Environment variable names only, never values.