Integration

Apify integration

Web scraping and automation platform API. Run pre-built scrapers (Actors) or deploy custom ones to extract data from any website. Features include Actor execution, dataset management, key-value storage, request queues, and scheduling. Access 2,000+ ready-made scrapers for social media, e-commerce, search engines, and more. Perfect for data extraction, web automation, and building data pipelines.

Connect Apify How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Apify.Built from the 43 Apify tools below, on the connection you add once.

Common Apify use cases

task management
webhook management
inspecting configuration
storage auditing
debugging build failures
data cleanup
data lifecycle
error recovery
resource cleanup
run history

What you can do with Apify

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.

Run, 6 operations

abort_runAbort runPOSTAborts a running Actor execution immediately. Run status changes to ABORTED. Partial results may be available in the dataset. Resources are released.
get_runGet runGETRetrieves current status and details of an Actor run. Returns status (READY, RUNNING, SUCCEEDED, FAILED, etc.), timing info, and dataset/store IDs. Poll periodically to monitor async runs.
resurrect_runResurrect runPOSTResurrects a finished Actor run, restarting its container with the same storages. Only works for runs with terminal status (SUCCEEDED, FAILED, ABORTED, TIMED-OUT). Run status changes to RUNNING.
run_actorRun actorPOSTRuns an Actor (web scraper or automation) with provided input. Actor ID can be your own or a public one like 'apify/web-scraper'. Input is passed in request body. Returns run object with ID for monitoring. Use waitForFinish for short runs.
run_actor_syncRun actor syncPOSTRuns an Actor synchronously and returns results immediately when complete. Connection held up to 5 minutes. Returns dataset items directly instead of run object. Best for quick extractions.
run_taskRun taskPOSTRuns an Actor task using its saved configuration. Optionally override input by passing JSON body. Override timeout, memory, or build with query params. Returns run object.

Actor, 4 operations

create_actorCreate actorPOSTCreates a new Actor on the Apify platform. Define name, description, source type, and default run options. Returns the created Actor object with ID.
delete_actorDelete actorDELETEPermanently deletes an Actor and all its versions and builds. This action cannot be undone. Associated runs, datasets, and stores are NOT deleted.
get_actorGet actorGETRetrieves detailed information about an Actor. Returns description, input schema, default run options, versions, and usage stats. Essential for understanding Actor capabilities before running.
update_actorUpdate actorPUTUpdates an existing Actor's settings. Modify name, description, default run options, visibility, or version configuration. Returns the updated Actor object.

Schedule, 4 operations

create_scheduleCreate schedulePOSTCreates a schedule for automatic recurring Actor runs. Define timing with cron expression, specify Actor/task to run, and configure input. Schedule runs automatically at specified times.
delete_scheduleDelete scheduleDELETEPermanently deletes a schedule. Scheduled runs will no longer execute. Past runs and their data are NOT affected. Returns 204 No Content.
get_scheduleGet scheduleGETRetrieves details of a specific schedule. Returns name, cron expression, timezone, actions, enabled status, and next run time. Use to inspect schedule configuration.
update_scheduleUpdate schedulePUTUpdates a schedule's configuration. Modify cron expression, actions, timezone, or enable/disable. Only provided fields are updated. Returns updated schedule object.

Dataset, 3 operations

create_datasetCreate datasetPOSTCreates a named dataset for storing structured data. If a dataset with the given name already exists, returns the existing one. Named datasets persist until explicitly deleted.
delete_datasetDelete datasetDELETEPermanently deletes a dataset and all its stored items. This action cannot be undone. Returns 204 No Content on success.
get_datasetGet datasetGETRetrieves metadata about a dataset. Returns item count, creation date, size, and access info. Use to check dataset size before fetching items.

Key value record, 3 operations

delete_key_value_store_recordDelete key value store recordDELETEDeletes a record from a key-value store by its key. Returns 204 No Content on success. The record is permanently removed.
get_key_value_store_recordGet key value store recordGETRetrieves a record from a key-value store by its key. Key-value stores hold any data type: JSON, images, PDFs, etc. Returns the record content with appropriate content type.
put_key_value_store_recordPut key value store recordPUTStores a record in a key-value store. Set Content-Type header to match data type (application/json, image/png, etc.). Overwrites existing record with same key.

Task, 3 operations

create_taskCreate taskPOSTCreates an Actor task with saved Actor ID, input, and run options. Tasks allow running the same Actor with predefined settings repeatedly. Returns the created task with ID.
delete_taskDelete taskDELETEPermanently deletes an Actor task. This action cannot be undone. Associated runs and their data are NOT deleted. Returns 204 No Content.
get_taskGet taskGETRetrieves details of an Actor task. Returns saved input, run options, linked Actor, and stats. Use to inspect task configuration before running.

Build, 2 operations

abort_buildAbort buildPOSTAborts a running Actor build immediately. Build status changes to ABORTED. Use when a build is stuck or no longer needed.
get_buildGet buildGETRetrieves details of a specific Actor build. Returns status, build number, start/finish times, and version info. Use to monitor build progress or check build details.

Dataset items, 2 operations

get_dataset_itemsGet dataset itemsGETRetrieves items (results) from an Apify dataset. Datasets store output from Actor runs. Get results in JSON, CSV, XML, or other formats. Supports pagination and field selection.
push_itemsPush itemsPOSTPushes (appends) items to a dataset. Send a JSON array of objects in the request body. Items are appended to the end of the dataset. Returns 201 Created on success.

Requests, 2 operations

batch_add_requestsBatch add requestsPOSTAdds multiple URL requests to a queue in one batch (max 25). Returns processedRequests and unprocessedRequests arrays. Use exponential backoff for retrying unprocessed items.
list_requestsList requestsGETLists requests in a request queue. Returns URLs, their status (pending/handled), and metadata. Use the cursor param for cursor-based pagination.

Webhook, 2 operations

create_webhookCreate webhookPOSTCreates a webhook that fires when specified events occur. Define event types (run succeeded, failed, etc.), target URL, and which Actor/task to watch. Returns created webhook with ID.
delete_webhookDelete webhookDELETEPermanently deletes a webhook. It will no longer fire for any events. Returns 204 No Content on success.

Actors, 1 operation

list_actorsList actorsGETLists Actors accessible to your account. Set my=true for your own Actors only. Returns Actor IDs, names, descriptions, and run counts. Use to discover available scrapers.

Builds, 1 operation

list_buildsList buildsGETLists all builds of an Actor. Returns build IDs, status, version info, and timestamps. Builds are compiled versions of the Actor's source code ready to run.

Datasets, 1 operation

list_datasetsList datasetsGETLists all datasets in your account. Returns dataset IDs, names, item counts, and creation dates. Datasets are created automatically for each Actor run or can be created manually.

Key value keys, 1 operation

list_keysList keysGETLists all keys in a key-value store. Returns key names, sizes, and public record URLs. Use exclusiveStartKey for cursor-based pagination through large stores.

Key value stores, 1 operation

list_key_value_storesList key value storesGETLists all key-value stores in your account. Returns store IDs, names, creation dates, and access info. Each Actor run creates a default key-value store.

Request, 1 operation

add_requestAdd requestPOSTAdds a single URL request to a request queue. Provide URL and optional metadata. Set forefront=true for priority processing. Duplicate URLs (by uniqueKey) are ignored.

Request queue, 1 operation

create_request_queueCreate request queuePOSTCreates a named request queue for managing URLs to crawl. If a queue with the given name already exists, returns the existing one (idempotent). Returns queue object with ID.

Runs, 1 operation

list_runsList runsGETLists all runs of an Actor with status and metadata. Filter by status, sort by date, paginate results. Returns run IDs, status, timing, and dataset IDs for each run.

Schedules, 1 operation

list_schedulesList schedulesGETLists all schedules for automated Actor runs. Returns schedule IDs, names, cron expressions, and associated Actor/task info. Use to manage recurring scraping jobs.

Tasks, 1 operation

list_tasksList tasksGETLists all Actor tasks in your account. Tasks are saved configurations (Actor + input) that can be run repeatedly. Returns task IDs, names, and linked Actor info.

User, 1 operation

get_userGet userGETRetrieves information about the authenticated user. Returns account details and plan limits. Use to verify account configuration and read plan ceilings.

Webhooks, 1 operation

list_webhooksList webhooksGETLists all webhooks in your account. Returns webhook IDs, event types, target URLs, and associated Actors/tasks. Use to manage notification and integration hooks.

Use Apify from Claude Code, Cursor or Codex

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

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

Apify integration FAQ

What can you do with the Apify integration?

LiveContext exposes 43 operations on Apify, covering run, actor, schedule and dataset. Common uses include task management, webhook management and inspecting configuration.