Pmx Canvas logo

Pmx Canvas

Local MCP canvas for collecting evidence, curating agent context, and reviewing shared project work.

Install Pmx Canvas

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "pmx-canvas": {
      "command": "bunx",
      "args": [
        "pmx-canvas"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

pmx-canvas MCP server connects AI agents to a local PMX Canvas board for collecting, organizing, and reviewing project material. Agents can read curated context, add findings, update board content, and work alongside a person on the same canvas. Boards support notes, files, web pages, images, charts, code diffs, diagrams, links, and interactive views. Reach for it when ongoing research or decisions need visible evidence that can persist across agent sessions.

Use cases

  • Collect research evidence on a persistent board
  • Pin project context for an agent's next task
  • Review and organize agent-generated findings
  • Export a board as a self-contained presentation

Key features

  • Local persistent canvas boards
  • Pinned context for agent requests
  • Cards for notes, files, charts, images, and diagrams
  • Evidence links and review dates
  • MCP and Agent Plugins 1.0 connectivity
  • HTML export, snapshots, and backups

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · pmx-canvas (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars30Stargazers on the source repository.
npm downloads2.2kPackage downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.

How Pmx Canvas works

What pmx-canvas does

pmx-canvas provides a shared, local workspace where people and AI agents organize the material behind a task. A board can contain notes, files, web pages, images, charts, code diffs, diagrams, and richer interactive views. Cards can be arranged on an infinite canvas, grouped, connected with labeled links, and placed in folders for later retrieval.

The MCP connection lets an agent work with that board instead of relying only on the current conversation. You can pin cards or entire boards to select the context for an agent's next step. The agent can then return findings, summaries, task updates, or other material to the board for review and further editing.

How it works

Boards are stored locally in .pmx-canvas/canvas.db within the project folder. Reopening the canvas from that same folder preserves the board across sessions. The application runs locally, and connected agents share the open board rather than using built-in multi-user accounts.

The canvas supports evidence-oriented workflows. The board can also be presented as a guided tour or exported as a self-contained HTML file. Undo, snapshots, and backup commands provide ways to manage board history and copies.

Setup and configuration

The recommended setup uses Node.js with npm and the PMX Canvas skill:

Terminal
npx skills add pskoett/pmx-canvas/skills/pmx-canvas

The skill guides the agent through installing the application, connecting to it, starting the canvas, and handling required permissions.

For manual use, install Bun 1.4.4 or newer and run the application from the folder where boards should be stored:

bash
bunx pmx-canvas

Use bunx pmx-canvas --demo in an empty folder to open a sample board. A global installation is also available with bun add -g pmx-canvas, followed by pmx-canvas.

An MCP client can launch the server with bunx pmx-canvas --mcp:

config.json
{
  "mcpServers": {
    "canvas": {
      "command": "bunx",
      "args": ["pmx-canvas", "--mcp"]
    }
  }
}

Start the agent in the same project folder as the canvas, then approve or enable the connection in the client. A plugin is another option for clients supporting the Agent Plugins 1.0 standard and MCP stdio connections.

Tools and capabilities

  • Read material selected through pinned cards and boards.
  • Add findings and other agent-generated material to a board.
  • Edit board content and update task-related material.
  • Organize cards with groups, folders, links, annotations, search, and a board map.
  • Build dashboards, comparisons, and interactive views on the canvas.
  • Review agent changes and see what an agent has read or added.
  • Present boards as tours or export them as standalone HTML.

Limitations and notes

PMX Canvas has no built-in multi-user accounts. Agents connected to the same open board share its content. Material requested from an agent may pass through that agent's tools and model provider; web content and hosted applications may also involve their external services.

Autosave writes to the project-local database but is not a backup. Use the documented backup and restore commands when a separate copy is needed. Client setup varies, and a client-specific plugin or direct MCP configuration may be required.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Pmx Canvas

pmx-canvas is an MCP server that connects AI agents to a local PMX Canvas board. Its main tools let agents read selected cards and boards, add findings, update material, and work with curated project context alongside a person. Boards store evidence, notes, files, links, and other work across sessions.

Install Bun 1.4.4 or newer, then configure your MCP client to run `bunx pmx-canvas --mcp`. You can also install the PMX Canvas skill with `npx skills add pskoett/pmx-canvas/skills/pmx-canvas`, which guides setup and connection.

Yes, pmx-canvas works with Claude Code through MCP. Configure Claude Code to launch `bunx` with the `pmx-canvas` and `--mcp` arguments, or use the PMX Canvas skill to guide installation and setup.

pmx-canvas saves boards in `.pmx-canvas/canvas.db` inside the project folder. Return to the same folder to reopen the board. Autosave is not a backup, so use the backup commands for a separate copy.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewPmx Canvas AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/pmx-canvas?style=directory)](https://allmcps.com/mcp/pmx-canvas)
HTML Embed
<a href="https://allmcps.com/mcp/pmx-canvas"><img src="https://allmcps.com/api/badge/pmx-canvas?style=directory" alt="Pmx Canvas on AllMCPs" /></a>