Integration

AWS Glue integration

AWS Glue serverless ETL service API. Manage data catalogs, crawlers, jobs, triggers, and workflows for data integration. Discover, prepare, and combine data for analytics, ML, and applications.

Connect AWS Glue How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in AWS Glue.Built from the 39 AWS Glue tools below, on the connection you add once.

Common AWS Glue use cases

automate crawler management
automate table management
automate trigger management
automate database management
automate job management
automate job run management
automate partition management
get job programmatically
get table programmatically
get crawler programmatically

What you can do with AWS Glue

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.

Crawler, 7 operations

create_crawlerCreate crawlerPOSTCreates a new crawler with specified targets, role, configuration, and optional schedule.
delete_crawlerDelete crawlerPOSTRemoves a specified crawler from the Data Catalog, unless the crawler state is RUNNING.
get_crawlerGet crawlerPOSTRetrieves metadata for a specified crawler.
get_crawlersGet crawlersPOSTRetrieves metadata for all crawlers defined in the customer account.
start_crawlerStart crawlerPOSTStarts a crawl using the specified crawler, regardless of what is scheduled. If the crawler is already running, returns a CrawlerRunningException.
stop_crawlerStop crawlerPOSTIf the specified crawler is running, stops the crawl.
update_crawlerUpdate crawlerPOSTUpdates a crawler. Stop the crawler first if it is currently running.

Database, 5 operations

create_databaseCreate databasePOSTCreates a new database in the Data Catalog.
delete_databaseDelete databasePOSTRemoves a specified database from a Data Catalog.
get_databaseGet databasePOSTRetrieves the definition of a specified database from the Data Catalog.
get_databasesGet databasesPOSTRetrieves all databases defined in a given Data Catalog.
update_databaseUpdate databasePOSTUpdates an existing database definition in a Data Catalog.

Job, 5 operations

create_jobCreate jobPOSTCreates a new job definition.
delete_jobDelete jobPOSTDeletes a specified job definition. If the job definition is not found, no exception is thrown.
get_jobGet jobPOSTRetrieves an existing job definition.
get_jobsGet jobsPOSTRetrieves all current job definitions.
update_jobUpdate jobPOSTUpdates an existing job definition. The previous definition is completely overwritten.

Table, 5 operations

create_tableCreate tablePOSTCreates a new table definition in the Data Catalog.
delete_tableDelete tablePOSTRemoves a table definition from the Data Catalog.
get_tableGet tablePOSTRetrieves the Table definition in a Data Catalog for a specified table.
get_tablesGet tablesPOSTRetrieves the definitions of some or all of the tables in a given Database.
update_tableUpdate tablePOSTUpdates a metadata table in the Data Catalog.

Trigger, 5 operations

create_triggerCreate triggerPOSTCreates a new trigger.
delete_triggerDelete triggerPOSTDeletes a specified trigger. If the trigger is not found, no exception is thrown.
get_triggerGet triggerPOSTRetrieves the definition of a trigger.
get_triggersGet triggersPOSTGets all the triggers associated with a job.
start_triggerStart triggerPOSTStarts an existing trigger. See Triggers for information about how different types of trigger are started.

Job run, 4 operations

get_job_runGet job runPOSTRetrieves the metadata for a given job run.
get_job_runsGet job runsPOSTRetrieves metadata for all runs of a given job definition.
start_job_runStart job runPOSTStarts a job run using a job definition.
stop_job_runStop job runPOSTStops a specified triggered crawl run; the specified JobRun must be in the RUNNING state.

Partition, 3 operations

create_partitionCreate partitionPOSTCreates a new partition in the Data Catalog.
delete_partitionDelete partitionPOSTDeletes a specified partition from a specified table.
get_partitionsGet partitionsPOSTRetrieves information about the partitions in a table.

Workflow, 2 operations

create_workflowCreate workflowPOSTCreates a new workflow.
get_workflowGet workflowPOSTRetrieves resource metadata for a workflow.

Workflow run, 2 operations

get_workflow_runGet workflow runPOSTRetrieves the metadata for a given workflow run, including status, timestamps, and run statistics.
start_workflow_runStart workflow runPOSTStarts a new run of the specified workflow.

Catalog import status, 1 operation

get_catalog_import_statusGet catalog import statusPOSTRetrieves the status of a migration operation.

Use AWS Glue from Claude Code, Cursor or Codex

Connect AWS Glue in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its AWS Glue 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 AWS Glue

Create your workspace
Sign up free. Nothing to install.
Connect AWS Glue once
Add your AWS Glue 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.

AWS Glue integration FAQ

What can you do with the AWS Glue integration?

LiveContext exposes 39 operations on AWS Glue, covering crawler, database, job and table. Common uses include automate crawler management, automate table management and automate trigger management.