1. Conduid
  2. Developer Tools
  3. Openai Appsdk Kanban
MCP server · Developer Tools

Openai Appsdk Kanban

by · github.com/GaetanJuvin/OpenAI-AppSDK-Kanban

MCP server: Openai Appsdk Kanban

Unclaimed last commit a year ago devtools
InstallView source
39Low

Scored 5 months ago · breakdown

About Openai Appsdk Kanban

Openai Appsdk Kanban is an MCP server published by GaetanJuvin in the Developer Tools category: mCP server: Openai Appsdk Kanban.

The repository has 1 stars and 0 forks, with the last commit a year ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/GaetanJuvin/OpenAI-AppSDK-Kanban

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Openai Appsdk Kanban

Powered by Claude · Grounded in docs

I know everything about Openai Appsdk Kanban. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 8 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • !License declaredNo license file. Legally you have no right to use it in a product.
  • !Tests presentNo tests found. Behaviour changes may go unnoticed between versions.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

Kanban MCP Server (Apps SDK Tutorial)

This repo follows the structure from Set up your server in the OpenAI Apps SDK docs. It bundles a tiny kanban component and an MCP server that exposes a single tool wired to that component.

Project layout

  • src/server.ts – TypeScript MCP server built with @modelcontextprotocol/sdk.
  • web/dist/kanban.{js,css} – Static component bundle returned by the MCP resource.
  • dist/ – Transpiled JavaScript after npm run build.

Prerequisites

  • Node.js 20+
  • npm (ships with Node)

Install dependencies once:

npm install

Run locally

  1. Build the component bundle (already checked in under web/dist, update and rebuild as needed).
  2. Start the MCP server: 
    npm run dev
    The server listens on http://localhost:3333/mcp and exposes a /health probe.
  3. Point MCP Inspector at the local endpoint, list tools, and invoke kanban-board. Inspector verifies that the response includes structured content plus component metadata and renders the kanban widget inline.
    • To add a new task, call the same tool with a newTask payload, for example: 
      {
  "name": "kanban-board",
  "arguments": {
    "newTask": {
      "title": "Kickoff marketing plan",
      "assignee": "Grace",
      "status": "in-progress"
    }
  }
}
      The server stores the task in-memory, echoes a confirmation message, and returns the refreshed board.

To ship production assets, compile with:

npm run build
npm run start

How it works

  • The MCP server registers the ui://widget/kanban-board@v4.html resource with mimeType: text/html+skybridge, sending the pre-built HTML that bootstraps the component bundle.
  • The kanban-board tool returns structuredContent, optional textual content, and _meta payload. _meta.openai/outputTemplate links the tool to the component. Passing a newTask object in the tool arguments persists the task in-memory and includes the updated board in the response.
  • The component reads window.openai.toolOutput to hydrate the kanban DOM and updates automatically when Inspector (or ChatGPT) delivers fresh tool output.

From here you can:

  • extend sampleTasks in src/server.ts with real data sources,
  • enhance the component under web/ (bundle via your preferred build tool),
  • expose the service publicly via HTTPS (e.g. ngrok http 3333) when registering a connector in ChatGPT developer mode.

Happy hacking!

OpenAI-AppSDK-Kanban

README fetched from the repository 8 days ago. The original is authoritative.

Questions

About Openai Appsdk Kanban

How do I install Openai Appsdk Kanban?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Openai Appsdk Kanban safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 3 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Openai Appsdk Kanban still maintained?

The last commit was a year ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.