Integration

Stackby integration

Stackby stacks over the v1 developer API: list rows of a table with filters and sorts, create, update and delete rows in batches, list the views and columns of a table, and upload a file so its URL can be stored in an attachment column.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Stackby.Built from the 7 Stackby tools below, on the connection you add once.

Common Stackby use cases

  • attaching a generated file to a Stackby row
  • writing collected data into a Stackby table
  • cleaning up rows a workflow has already processed
  • writing a computed status back onto existing rows
  • mapping column names before creating or updating rows
  • pulling the contents of a Stackby table into a workflow
  • reusing an existing view filter rather than writing one
  • reading only the rows matching a text filter

What you can do with Stackby

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Row, 4 operations

  • create_rowsCreate rowsPOSTCreates rows in a Stackby table and returns the created row objects.
  • delete_rowsDelete rowsDELETEDeletes the given row ids from a Stackby table.
  • list_rowsList rowsGETReturns rows of a Stackby table as objects carrying an id and a field map.
  • update_rowsUpdate rowsPATCHUpdates the listed columns on existing rows, leaving other columns untouched.

Column, 1 operation

  • list_columnsList columnsGETReturns the columns of a table with their names and types.

File, 1 operation

  • upload_fileUpload filePOSTUploads a file to Stackby storage and returns its public URL.

View, 1 operation

  • list_viewsList viewsGETReturns the views of a table, so a view can be named when listing rows.

Use Stackby from Claude Code, Cursor or Codex

Connect Stackby in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Stackby operations become tools the client can call, next to every other integration you connected.

Claude Code
claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"
Codex (~/.codex/config.toml)
[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"
Cursor, Claude Desktop and other JSON configs
{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Stackby

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect Stackby once

    Add your Stackby connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. Describe the job in chat

    The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Stackby integration FAQ

What can you do with the Stackby integration?

LiveContext exposes 7 operations on Stackby, covering row, column, file and view. Common uses include attaching a generated file to a Stackby row, writing collected data into a Stackby table and cleaning up rows a workflow has already processed.

Popular integrations

Browse the whole catalog