Labsco
its-dart logo

DevvyBoard

from its-dart

Connect AI coding tools (Cursor, Claude Code, Codex CLI) to your DevvyBoard Kanban workspace. List projects, read boards, and create, update, move, or delete cards — all from inside your editor via a local stdio server.

🔥🔥🔥✓ VerifiedPaid serviceNeeds API keys
#automation#payments#search#maps

DevvyBoard

Team workspace

Developer docs

MCP Integration

Connect AI coding tools to your DevvyBoard projects. With the Model Context Protocol integration, Cursor, Claude Code, and Codex CLI can read boards, create and move cards, triage ideas, post in chat (and summon @devvy), publish roadmaps, and read or draw your project Blueprint — without leaving your editor.

Create an API keynpm: devvyboard-mcp

Overview

DevvyBoard exposes a Model Context Protocol (MCP) server that AI assistants can call as tools. Once configured, your AI assistant can:

  • List all projects your API key is authorised for

  • Read the full Kanban board — columns, card groups, and cards — for any project

  • Create, update, move, and delete cards (write scope required)

  • Triage the ideas backlog and promote ideas onto the board

  • Post in project chat — mentioning @devvy summons the AI teammate

  • Publish or unpublish the public roadmap (owner only)

  • Read the project Blueprint as a compact outline or full node-graph doc

  • Draw on the Blueprint: create or extend the canvas and link nodes to cards — no coordinates needed, layout is automatic

The MCP package is published as devvyboard-mcp on npm. It runs as a local stdio server with npx -y devvyboard-mcp — no additional service or infrastructure is required on your machine.

Get an API key

API keys are scoped to specific projects and carry either read or read-and-write permissions. You can create and revoke keys at any time.

1

Sign in to DevvyBoard on web. Click your profile picture (top-right) and choose Connectivity. Or go directly to /connectivity.

2

Click Create API key.

3

Give the key a name (for example, Cursor MCP ), select the projects to grant access to, and choose whether the key should have read or read and write scope.

4

Click Create. Copy the key shown — it begins with dbk_live_ and is displayed only once.

Store the key in your OS keychain or password manager. If you lose it, revoke the key from the Connectivity page and create a new one.

Cursor

Add the DevvyBoard MCP server to your Cursor configuration. Cursor reads MCP servers from ~/.cursor/mcp.json (global) or a .cursor/mcp.json file at the root of any project (project-scoped).

{
 "mcpServers": {
 "devvyboard": {
 "command": "npx",
 "args": ["-y", "devvyboard-mcp"],
 "env": {
 "DEVVYBOARD_API_KEY": "dbk_live_YOUR_KEY_HERE"
 }
 }
 }
}

1

Open or create the file at ~/.cursor/mcp.json (on Windows: %USERPROFILE%\.cursor\mcp.json).

2

Paste the configuration above, replacing dbk_live_YOUR_KEY_HERE with your actual API key from Connectivity.

3

In Cursor, open the Command Palette (Ctrl+Shift+P on Windows/Linux, Cmd+Shift+P on Mac) and run MCP: Restart all servers.

4

The devvyboard server and its tools should appear in the MCP panel. Ask the AI agent to “list my DevvyBoard projects” to confirm connectivity.

Claude Code

Claude Code uses a claude_desktop_config.json file for MCP configuration. Add the DevvyBoard server under the mcpServers key.

Config file location by platform:

  • macOS / Linux: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

1

Open or create the config file at the path above for your platform.

2

Add the devvyboard entry under mcpServers, replacing the placeholder key.

3

Restart Claude Code. The DevvyBoard tools will appear in the tools panel.

Codex CLI

Codex CLI supports MCP servers via a codex.json configuration file in your project root or home directory.

Alternatively, export the key as an environment variable before running Codex:

export DEVVYBOARD_API_KEY=dbk_live_YOUR_KEY_HERE
codex

Refer to the Codex CLI documentation for the exact config file path on your version.

Available tools

The MCP server exposes the following tools. Each tool call targets the DevvyBoard REST API on your behalf using the API key supplied in your configuration.

Tool Description Min. scope list_projects List all projects accessible with this API key. read get_board Return the columns, card groups, and cards for a project. read get_card Fetch full details for a single card by ID. read create_card Add a new card to a specified column. write update_card Change a card's title, description, priority, or deadline. write move_card Move a card to a different column at a given position. write delete_card Permanently delete a card from the board. write list_ideas List the project's ideas backlog. read create_idea Add an idea to the backlog. write promote_idea Promote an idea to a card in a chosen column. write post_chat_message Post to the project chat room; @devvy summons the Devvy AI agent. write get_roadmap Public roadmap page state and URL. read set_roadmap_published Publish or unpublish the public roadmap (owner only). write list_wireframes List the project's Blueprints (vision canvases). read get_wireframe Read a Blueprint as a compact outline or the full node-graph doc. read create_wireframe Create a Blueprint from nodes and edges — the server handles layout. write add_to_wireframe Add nodes/edges to a Blueprint without moving anything the team placed. write update_wireframe Atomic granular edits: add, update, remove nodes and connections. write link_node_to_card Link Blueprint nodes to kanban cards to show build progress on the vision. write

The Blueprint tools (*_wireframe, link_node_to_card) work on projects whose organisation is on DevvyBoard Pro. Every Blueprint write automatically saves a restore point first, so anything an agent draws is one click away from undone.

Scopes

Every API key carries one of two scope levels. You choose the scope when creating the key from Connectivity.

Read

The key can list projects, read boards, and fetch individual cards. It cannot make any changes.

Suitable for AI assistants that summarise work or answer questions about tasks.

Read and Write

The key can read everything plus create, update, move, and delete cards.

Suitable for AI agents that manage your board on your behalf.

Prefer read-only keys when an AI tool only needs to look up tasks. Limit write access to agents you fully trust to modify your board.

API limits

Each HTTP call under /api/integrations/v1/* counts toward your quota (MCP tools map one-to-one). Exceeding a limit returns HTTP 429 with rate-limit headers — not a silent throttle.

Limit Free Pro (incl. legacy Team) Active API keys 2 10 Daily API requests 300 10,000 Daily writes 50 2,000 Burst (all methods) 20 / minute 120 / minute Scopes read + write read + write

Pro is for higher headroom, not exclusive MCP access. Upgrade from billing in the mobile app when you need more daily requests.