AI Workflow Planner

MCP Server

Connect AI agents directly to your tasks using the Model Context Protocol (MCP). Works with Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP-compatible client.

What is MCP?

MCP (Model Context Protocol) is an open standard that lets AI assistants connect to external tools and data sources. Instead of copying prompts and pasting API responses, your AI agent talks directly to is.team — reading your tasks, creating new ones, and managing your workflow in real time.

Available Tools

The MCP server exposes 6 tools, matching the LLM API endpoints:

Tool	Permission	Description
list_cards	Token only	Discover all cards you can access — IDs, titles, workspaces
read_card	LLM Access	Read card as markdown — tasks, details, notes, connections
create_task	Actions	Create a new task with title, type, priority, and more
update_task	Actions	Update any task field — set to null to clear
complete_task	Actions	Mark a task as done, get move suggestions
move_task	Actions	Move a task to a connected card
add_comment	Comments	Add a comment to any task

Prerequisites

Enable LLM Access on the board card you want to expose (card context menu → AI Integration)
Generate an API token from Account Settings → API tab
Copy the card ID from the AI Integration modal URL (e.g. col-1773256154568)

Option 1: Remote Server (Recommended)

The remote MCP server is hosted at https://is.team/mcp. No installation required — just add the URL to your MCP client configuration.

Claude Desktop

Add to your claude_desktop_config.json:

json

{
  "mcpServers": {
    "is-team": {
      "url": "https://is.team/mcp",
      "headers": {
        "Authorization": "Bearer ist_your_token_here"
      }
    }
  }
}

Claude Code

Add the remote server from the CLI:

bash

claude mcp add is-team \
  --transport http \
  --url https://is.team/mcp \
  --header "Authorization: Bearer ist_your_token_here"

Cursor / Windsurf

Add to your project's .cursor/mcp.json or global MCP config:

json

{
  "mcpServers": {
    "is-team": {
      "url": "https://is.team/mcp",
      "headers": {
        "Authorization": "Bearer ist_your_token_here"
      }
    }
  }
}

Option 2: Local Package (stdio)

For clients that prefer stdio-based MCP servers, install the @isteamhq/mcp package. It runs locally and proxies to the is.team API.

Claude Desktop

json

{
  "mcpServers": {
    "is-team": {
      "command": "npx",
      "args": ["@isteamhq/mcp"],
      "env": {
        "IST_API_TOKEN": "ist_your_token_here"
      }
    }
  }
}

Claude Code

bash

claude mcp add is-team -- npx @isteamhq/mcp \
  --env IST_API_TOKEN=ist_your_token_here

Environment variables

IST_API_TOKEN (required) — your ist_ API token
IST_BASE_URL (optional) — defaults to https://is.team

Per-Card Access Control

MCP tools respect the same per-card permissions as the LLM API. Each card can independently enable:

LLM Access — required for read_card
Actions — required for create_task, update_task, complete_task, move_task
Comments — required for add_comment

Configure these from the card's context menu → AI Integration.

Tip

The cardId is passed as an argument to each tool call. You can work with multiple cards in the same MCP session.

PreviousLLM API NextPlans & Pricing