Integration

Keboola Job Queue integration

The Keboola Job Queue API runs the components of a Keboola project: start a job for an extractor, writer, transformation, application or flow configuration (now or after a delay, optionally with variable values or only some configuration rows or flow tasks), read a job and its result, search past jobs by component, configuration, status or time, stop a running job, read a job's input and output tables as OpenLineage events, see which tasks of a flow job can be run again, and read the project's total job duration. A job runs on its own: follow it with get_job until isFinished is true; isSuccess then says whether it delivered. Jobs act for real: a writer job writes to its external system even in debug mode. Left out: the deprecated job list routes and the grouped job search. The connection asks for the same two values as the Keboola Storage connection: the domain of your Keboola stack, the part after connection. in the address you sign in at: keboola.com (AWS US Virginia), us-east4.gcp.keboola.com (GCP US Virginia), eu-central-1.keboola.com (AWS EU Frankfurt), north-europe.azure.keboola.com (Azure EU Ireland) or europe-west3.gcp.keboola.com (GCP EU Frankfurt); for a single-tenant stack, the part after connection. in its own address. It also asks for a Storage API token from Project Settings, API Tokens, sent in the X-StorageApi-Token header.

Connect Keboola Job Queue How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

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

What you can do with Keboola Job Queue

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.

Job, 3 operations

create_jobCreate jobPOSTStarts a job that runs a component configuration (an extractor, writer, transformation, application or flow) and returns it. The job acts for real; follow it with get_job until isFinished.
get_jobGet jobGETReturns one job: its status, whether it finished and succeeded, the component and configuration it ran, timing, result and metrics.
search_jobsSearch jobsGETSearches the project's jobs by ID, run, branch, component, configuration, status, mode, type or time window, newest first by default.

Kill, 1 operation

kill_jobKill jobPOSTAsks Keboola to stop a job: a job still created or waiting is cancelled, one already processing is terminated. Returns the job, now with desiredStatus terminating.

Open api lineage, 1 operation

get_job_lineageGet job lineageGETReturns the OpenLineage events of an executed job: the tables it read (input mapping) and wrote (output mapping); for flow and container jobs the child jobs are included.

Orchestration rerun plan, 1 operation

get_flow_rerun_planGet flow rerun planGETLists the tasks of a flow job that can be run again, each with its last job, component, configuration and status.

Project, 1 operation

get_project_job_statsGet project job statsGETReturns the total duration, in seconds, of all processed jobs of the project.

Use Keboola Job Queue from Claude Code, Cursor or Codex

Connect Keboola Job Queue in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Keboola Job Queue 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 Keboola Job Queue

Create your workspace
Sign up free. Nothing to install.
Connect Keboola Job Queue once
Add your Keboola Job Queue connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
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.