Thestandup

GitHub Actions

MCP server for Standup kanban board

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "thestandup-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y [email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add thestandup-mcp -- npx -y thestandup-mcp@1.7.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "thestandup-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 1.7.0
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Thestandup?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Thestandup need an API key?

No required environment variable is listed on this record.

What transport does Thestandup use?

Thestandup runs locally over stdio.

When was Thestandup last checked?

Last checked 2026-10-28. MCP server for Standup kanban board

From the publisher

Documentation

Standup MCP Server

An MCP server that connects AI coding agents (Claude Code, etc.) to Standup — a kanban board app. Once connected, the agent can list boards, read and create cards, move cards between columns, manage assignees, and post comments, all through natural conversation.

Prerequisites

A Standup account with a Pro or Enterprise membership (required for API keys)
Node.js 18+
An MCP-compatible client (e.g. Claude Code)

Setup

1. Create an API key in Standup

Go to thestandup.app and log in
Click the user menu (top-right) → API Keys
Give your key a name (e.g. "Claude Code") and click Create
Copy the key — it starts with sk- and is only shown once

2. Configure your MCP client

Claude Code

Run the following command, replacing sk-your-api-key-here with your API key from step 1:

claude mcp add standup \
  -e STANDUP_URL=https://www.thestandup.app \
  -e STANDUP_API_KEY=sk-your-api-key-here \
  -- npx -y thestandup-mcp

Then restart Claude Code for the server to connect.

Other MCP clients

The server uses stdio transport — any MCP client that can launch a subprocess will work. Set the STANDUP_URL and STANDUP_API_KEY environment variables and run:

npx -y thestandup-mcp

3. Verify the connection

Start a new Claude Code session and ask it to list your boards:

"List my standup boards"

You should see your boards returned. If you get an authentication error, double-check your API key.

Available tools

Tool	Description
`list_boards`	List all boards with name and column summary
`create_board`	Create a board from a template (`blank` or `ai-software-development`), with optional context and repository
`get_board`	Get a full board with columns, cards, context, and agents
`get_board_summary`	Compact board: columns with agents and one row per card (first line, assignees, stickers, work, comment count, last comment author and time), no comment bodies
`create_card`	Create a new card in a column
`update_card`	Update card text
`delete_card`	Delete a card
`move_card`	Move a card to a different column
`assign_card`	Assign a user, or a column agent as `agent:<identifier>`, to a card
`unassign_card`	Remove a user or column agent from a card
`search_cards`	Search for cards across all boards by text content
`get_comments`	Get all comments on a card
`add_comment`	Post a comment on a card (supports markdown, @mentions, clickable option buttons, and attribution to a column agent via `agentId`)
`update_board_context`	Set a board's project context and/or repository URL
`update_column_agents`	Replace a column's agents (send the full list)
`set_card_work`	Record where a card's work lives (repo path, branch, commits, pushed, PR link); merges with what's already recorded

Example usage

Once connected, you can interact with your boards in natural language:

"What's on my standup board?"
"Create a card in the To Do column: Refactor the auth middleware"
"Move the auth refactor card to In Progress"
"Add a comment to that card: Started work, estimating 2 hours"
"Assign me to the top card in In Progress"

Workflow conventions

The server includes built-in instructions that guide the AI agent to follow these conventions:

Assignment: each column agent assigns itself as agent:<identifier>; agents in the same column work in parallel
Priorities: resume cards handed back after a person replied, then take unfinished cards nobody is assigned to
Progress updates: add a comment (attributed with agentId) summarising what you did before unassigning, and record where code changes live with set_card_work (shown on the card)
Blockers: post a comment with clickable options, @mention the user and assign the card to them in place. Standup hands it back to the agent when they answer
Handed-back note: tool responses include a "Handed back to you" note while a card is waiting to be resumed
Pipeline flow: advance cards left-to-right through columns; reject by moving back with a comment
Running the pipeline: when asked to process a board, carry each card on through every agent column rather than stopping after one stage; board context is optional
Instruction length: Claude Code truncates server instructions at 4,096 characters, so a test keeps them under that limit

Keeping agents running

Agents only act while a session is running; Standup cannot start one. A card you hand back by replying or reassigning waits until a session next looks at the board. To have it picked up without asking, keep a session polling:

Claude Code: /loop 15m process the <board name> board
Other agents: a scheduler or cron job that starts the agent with the same prompt

Development

npm install
npm run build       # compile TypeScript
npm test            # run tests
npm run test:watch  # run tests in watch mode
npm run all         # type-check + test

License

MIT

Thestandup

GitHub Actions

MCP server for Standup kanban board

Devops Developer Tools

Add to Cursor Add to VS Code Run on PlugMCP

GitHub npm Website

Add to Cursor Add to VS Code Run on PlugMCP

1{2  "mcpServers": {3    "thestandup-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "[email protected]"8      ]9    }10  }11}

.cursor/mcp.jsonMCP server

Transport: stdio
Status: Local

Power your agent

Add this server

The publisher's own command. Not a PlugMCP endpoint.

Add to Cursor Add to VS Code Run on PlugMCP

Host a copy with our keys and logs.

Local command

npx -y [email protected]

Claude Code has no install link for a local command. Copy the command below and run it in a terminal.

shClaude Code

1claude mcp add thestandup-mcp -- npx -y thestandup-mcp@1.7.0

Run in a terminal.

jsonClaude Desktop

1{2  "mcpServers": {3    "thestandup-mcp": {4      "command": "npx",5      "args": [6        "-y",7        "[email protected]"8      ]9    }10  }11}

claude_desktop_config.json

Local · npmPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
Version: 1.7.0
Last checked: 2026-10-28

Stars: —
Tools: —
Uptime: —

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Questions

How do I install Thestandup?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Thestandup need an API key?

No required environment variable is listed on this record.

What transport does Thestandup use?

Thestandup runs locally over stdio.

When was Thestandup last checked?

Last checked 2026-10-28. MCP server for Standup kanban board

From the publisher

Documentation

Standup MCP Server

Prerequisites

A Standup account with a Pro or Enterprise membership (required for API keys)
Node.js 18+
An MCP-compatible client (e.g. Claude Code)

Setup

1. Create an API key in Standup

Go to thestandup.app and log in
Click the user menu (top-right) → API Keys
Give your key a name (e.g. "Claude Code") and click Create
Copy the key — it starts with sk- and is only shown once

2. Configure your MCP client

Claude Code

Run the following command, replacing sk-your-api-key-here with your API key from step 1:

claude mcp add standup \
  -e STANDUP_URL=https://www.thestandup.app \
  -e STANDUP_API_KEY=sk-your-api-key-here \
  -- npx -y thestandup-mcp

Then restart Claude Code for the server to connect.

Other MCP clients

The server uses stdio transport — any MCP client that can launch a subprocess will work. Set the STANDUP_URL and STANDUP_API_KEY environment variables and run:

npx -y thestandup-mcp

3. Verify the connection

Start a new Claude Code session and ask it to list your boards:

"List my standup boards"

You should see your boards returned. If you get an authentication error, double-check your API key.

Available tools

Tool	Description
`list_boards`	List all boards with name and column summary
`create_board`	Create a board from a template (`blank` or `ai-software-development`), with optional context and repository
`get_board`	Get a full board with columns, cards, context, and agents
`get_board_summary`	Compact board: columns with agents and one row per card (first line, assignees, stickers, work, comment count, last comment author and time), no comment bodies
`create_card`	Create a new card in a column
`update_card`	Update card text
`delete_card`	Delete a card
`move_card`	Move a card to a different column
`assign_card`	Assign a user, or a column agent as `agent:<identifier>`, to a card
`unassign_card`	Remove a user or column agent from a card
`search_cards`	Search for cards across all boards by text content
`get_comments`	Get all comments on a card
`add_comment`	Post a comment on a card (supports markdown, @mentions, clickable option buttons, and attribution to a column agent via `agentId`)
`update_board_context`	Set a board's project context and/or repository URL
`update_column_agents`	Replace a column's agents (send the full list)
`set_card_work`	Record where a card's work lives (repo path, branch, commits, pushed, PR link); merges with what's already recorded

Example usage

Once connected, you can interact with your boards in natural language:

"What's on my standup board?"
"Create a card in the To Do column: Refactor the auth middleware"
"Move the auth refactor card to In Progress"
"Add a comment to that card: Started work, estimating 2 hours"
"Assign me to the top card in In Progress"

Workflow conventions

The server includes built-in instructions that guide the AI agent to follow these conventions:

Assignment: each column agent assigns itself as agent:<identifier>; agents in the same column work in parallel
Priorities: resume cards handed back after a person replied, then take unfinished cards nobody is assigned to
Progress updates: add a comment (attributed with agentId) summarising what you did before unassigning, and record where code changes live with set_card_work (shown on the card)
Blockers: post a comment with clickable options, @mention the user and assign the card to them in place. Standup hands it back to the agent when they answer
Handed-back note: tool responses include a "Handed back to you" note while a card is waiting to be resumed
Pipeline flow: advance cards left-to-right through columns; reject by moving back with a comment
Running the pipeline: when asked to process a board, carry each card on through every agent column rather than stopping after one stage; board context is optional
Instruction length: Claude Code truncates server instructions at 4,096 characters, so a test keeps them under that limit

Keeping agents running

Claude Code: /loop 15m process the <board name> board
Other agents: a scheduler or cron job that starts the agent with the same prompt

Development

npm install
npm run build       # compile TypeScript
npm test            # run tests
npm run test:watch  # run tests in watch mode
npm run all         # type-check + test

License

MIT