Apify
Apify is a platform for building, deploying, and managing web scraping and automation tools, known as Actors.
Verdict
Common use cases
- Scrape competitor product pages daily
- Monitor review sites for brand mentions
- Extract job postings from career boards
- Automate lead generation from directories
- Pull pricing data for market analysis
Integration
- Vendor
- Apify
- Category
- other
- Auth
- API_KEY
- Tools
- 28
- Composio slug
apify
Tools
- Create Actor
Tool to create a new actor with specified configuration. use when you need to initialize a fresh actor programmatically before publishing or running it.
- Create Actor Task
Tool to create a new actor task with specified settings. use when you need to configure or schedule recurring actor runs programmatically.
- Create Dataset
Tool to create a new dataset. use when you need to initialize or retrieve a dataset by name.
- Create Task Webhook
Tool to create a webhook for an actor task. use when you need external notifications about task run events (e.g., completion or failure) in downstream systems.
- Delete Actordestructive
Tool to delete an actor permanently. use when you need to remove an actor by its id or username~actorname. confirm before calling.
- Delete Webhookdestructive
Tool to delete a webhook by its id. use when removing a webhook after confirming the webhook id.
- Get Actor Details
Tool to get details of a specific actor. use when you need actor metadata by id or username/actorname.
- Get all webhooks
Tool to get a list of all webhooks created by the user. use when you need to enumerate webhooks before filtering or maintenance.
- Get dataset items
Tool to retrieve items from a dataset. use when you need to fetch data from a specified dataset by pagination or filtering. only json format is fully supported.
- Get Default Build
Tool to get the default build for an actor. use after specifying the actor id; optionally wait for the build to finish before returning.
- Get Key-Value Record
Tool to retrieve a record from a key-value store. use when you need to fetch a specific value by key from an apify key-value store.
- Get list of builds
Tool to get a list of builds for a specific actor. use when you need paginated access to an actor’s build (version) history.
- Get list of runs
Tool to get a list of runs for a specific actor. use when you need to paginate through runs and optionally filter by status before processing run data.
- Get list of task runs
Tool to get a list of runs for a specific actor task. use when you need to paginate through task runs and optionally filter by status.
- Get list of tasks
Tool to fetch a paginated list of tasks belonging to the authenticated user. use when you need to browse or sort tasks created by the user.
- Get list of task webhooks
Tool to get a list of webhooks for a specific actor task. use when you need to review or paginate webhooks after creating or updating a task.
- Get log
Tool to retrieve logs for a specific actor run or build. use after initiating an actor run or build when you need to inspect execution logs.
- Get OpenAPI Definition
Tool to get the openapi definition for a specific actor build. use when you need the api schema for code generation or analysis.
- Get Task Input
Tool to retrieve the input configuration of a specific task. use when you need to inspect stored task input before execution or debugging.
- Resurrect Run
Tool to resurrect a finished actor run. use when you need to restart a completed or failed run. deprecated endpoint; may be removed in future.
- Run Actor Asynchronously
Tool to run a specific actor asynchronously. use when you need to trigger an actor run without waiting for completion and retrieve its run details immediately.
- Run Actor Sync
Tool to run a specific actor synchronously with input and return its output record. use when immediate actor results are needed; runs may timeout after 300 seconds.
- Run Actor Sync & Get Dataset Items
Tool to run an actor synchronously and retrieve its dataset items. use when immediate access to run results is needed.
- Run Task Asynchronously
Tool to run a specific actor task asynchronously. use when you need to trigger a task run without waiting for completion and immediately retrieve its run details.
- Store Data in Dataset
Tool to store data items in a dataset. use after collecting data when you want to batch-append or update items in an existing dataset.
- Store Data in Key-Value Store
Tool to create or update a record in a key-value store. use after you have the store id and record key to persist json data.
- Update Key-Value Store
Tool to update a key-value store's properties. use when renaming or changing access or schema version of the store after confirming the store id.
- Update Task Input
Tool to update the input configuration of a specific actor task. use when you need to modify a scheduled tasks input before execution.
Setup
Setup guide
- 11. In Switchy, open your workspace settings and navigate to the Integrations tab. 2. Find Apify in the MCP directory and click Connect. 3. You'll be prompted to paste an Apify API token — generate one by logging into your Apify account, going to Settings > Integrations, and creating a new Personal API Token with full permissions. 4. Copy the token, return to Switchy, paste it into the auth field, and click Authorize. 5. Switchy confirms the connection and shows Apify as active in your integrations list. 6. Open any Space, type '@Apify get actor details' followed by an actor ID or username~actorname, and send the message — if Apify responds with actor metadata, the integration is working. 7. To run an actor or create a dataset, use the same @mention pattern with the relevant tool name and parameters.
What teammates see: by default, memories from Apify are scoped to the Space (PROJECT visibility) - you can mark any memory PRIVATE or share it ORG-wide.
Works well with
Top models
Compatibility data appears once enough Spaces have used this MCP together with a given model.
How Switchy teams use it
Starter prompts
List My Actors
@Apify get a list of all actors in my account, including their names, IDs, and last modified dates.Open in a Space →
Run a Scraper
@Apify run the actor named 'competitor-price-scraper' with default settings and notify me when the run completes.Open in a Space →
Fetch Dataset Results
@Apify retrieve all items from the dataset named 'product-reviews-2024' and format them as a table.Open in a Space →
Create Webhook Alert
@Apify create a webhook for the task 'weekly-pricing-check' that posts to our Slack channel whenever a run succeeds or errors.Open in a Space →
Schedule Recurring Crawl
@Apify create a task for the actor 'linkedin-job-scraper' that runs every Monday at 9 AM UTC and saves results to a new dataset.Open in a Space →
Example outputs
Illustrative - representative of the model's voice and quality, not literal recordings.
@Apify list all my active webhooks and show me which ones are tied to dataset events
Here are your 7 active webhooks: **Dataset-related (3):** - Webhook ID abc123: Fires on DATASET.SUCCEEDED for 'product-scraper-output', sends to https://api.example.com/ingest - Webhook ID def456: Fires on DATASET.FAILED for 'competitor-prices', sends to Slack channel #alerts - Webhook ID ghi789: Fires on DATASET.SUCCEEDED for 'review-aggregator', sends to Zapier endpoint **Task-related (4):** - Webhook ID jkl012: Fires on ACTOR.RUN.SUCCEEDED for 'daily-scrape-task'... This is an illustrative example showing how Apify's webhook enumeration might surface event types and destinations.
Demonstrates read-heavy discovery across Apify's webhook system. Requires API key with webhook read permissions. Useful for auditing automation pipelines before modifying or deleting hooks. Real output structure depends on how many webhooks exist in your account.
@Apify create a new actor task called 'weekly-competitor-scan' using the Google Search Scraper actor, set it to run every Monday at 9am UTC
Created actor task 'weekly-competitor-scan' (ID: task_xyz789). **Configuration:** - Actor: apify/google-search-scraper - Schedule: Mondays at 09:00 UTC (cron: 0 9 * * 1) - Input: { "queries": ["competitor pricing SaaS"], "maxResults": 50 } - Default dataset: auto-generated on each run Task is now active. First run scheduled for next Monday. You can modify input parameters or schedule via the Apify Console or by calling update_actor_task with this task ID. This is an illustrative example of task creation with scheduling.
Shows write-action capability for recurring scraper workflows. Requires API key with actor.task:write scope. Side-effect: creates a billable scheduled task that will consume Apify platform credits on each run. Verify pricing and rate limits before production use.
@Apify pull the last 100 rows from my 'ecommerce-products' dataset and summarize which product categories have the most price changes this week
Fetched 100 items from dataset 'ecommerce-products' (last updated 2 hours ago). **Price change summary:** - **Electronics (34 items):** 18 price drops (avg -12%), 16 increases (avg +8%) - **Home & Garden (28 items):** 9 drops, 19 increases — notable spike in outdoor furniture - **Apparel (22 items):** Minimal movement, 3 seasonal clearance drops - **Books (16 items):** Stable pricing Electronics saw the most volatility. The dataset schema includes 'previousPrice' and 'currentPrice' fields, which enabled this comparison. This is an illustrative example showing dataset retrieval paired with AI analysis.
Combines Apify's dataset read tool with AI reasoning to surface trends. Requires dataset to exist and have structured price fields. Useful for competitive intelligence workflows. Real analysis quality depends on dataset schema consistency and update frequency.
Use-case deep-dives
When Apify beats building scrapers in-house for product teams
A 6-person e-commerce team needs daily competitor pricing on 2,000 SKUs across four marketplaces. Building scrapers in-house means maintaining anti-bot logic, proxy rotation, and parsing rules every time a site changes its DOM. Apify wins here because you create an Actor Task once, schedule it via webhook, and dump results into a Dataset that feeds your pricing dashboard. The trade-off: if you need sub-hourly updates or your competitors block Apify's infrastructure, you'll hit rate limits or need custom proxies. For daily or weekly cadence at this scale, Apify's 28 tools handle the orchestration so your team writes business logic, not scraper maintenance. If you're scraping fewer than 500 pages a day, a simpler HTTP client might be cheaper.
Why Apify's webhook tooling fits high-volume lead workflows
A 3-person sales ops team enriches 400 inbound leads per day by scraping LinkedIn profiles, company sites, and funding databases. They use Apify Actors to pull the data, then Create Task Webhook to trigger their CRM update when each Actor run completes. The API key auth keeps setup simple, and the Dataset tools let them batch-export results to Salesforce nightly. Apify works when the enrichment sources are public web pages and you can tolerate 5-10 minute latency per lead. If you need real-time enrichment or your sources require OAuth logins, Apify's Actor marketplace might not cover it and you'll write custom Actors. For this team's volume and latency tolerance, Apify's webhook-to-dataset flow is faster than duct-taping Puppeteer scripts.
When Apify's Actor library saves compliance teams from dev backlog
A 2-person compliance team at a consumer brand monitors 30 retailer sites weekly to catch unauthorized resellers and counterfeit listings. They don't have eng bandwidth to build scrapers, so they use Apify's pre-built Actors for Amazon, eBay, and Shopify, then Get Actor Details to confirm each Actor's schema before scheduling runs. Results land in Datasets, which they export to Google Sheets for manual review. Apify wins when the sites you monitor already have Actors in the marketplace and your review cadence is weekly or slower. If you need hourly checks or the marketplace doesn't cover your retailers, you'll wait on custom Actor development or hire a freelancer. For this team's 30-site, low-frequency use case, Apify's library beats a six-month dev queue.
Frequently asked
What does the Apify MCP do in Switchy?
It lets your team create, run, and manage Apify actors and tasks directly from Switchy's AI workspace. You can spin up new web scrapers, schedule recurring runs, create datasets, and wire up webhooks for run notifications—all without leaving the conversation. Useful if your team already uses Apify for data extraction or automation and wants AI to orchestrate those workflows.
Do I need an Apify API key to connect this MCP?
Yes. The integration uses API_KEY authentication, so you'll need a valid Apify API token from your account settings. Paste it into Switchy once; the MCP stores it securely and uses it for every tool call. Anyone on your Switchy workspace who connects the MCP can create or delete actors, so treat the key like admin access.
Can the Apify MCP trigger actor runs and wait for results?
The MCP can create actors, tasks, and webhooks, but the representative tools shown don't include a synchronous run-and-wait command. You'll likely create a task, start it via the Apify API separately, then use a webhook to notify Switchy when results land in a dataset. Check the full 28-tool list for run-triggering tools if your use case needs them.
How is this different from calling the Apify API directly?
The MCP wraps Apify's REST API into natural-language tools your AI can call mid-conversation. Instead of writing curl commands or Python scripts, you describe what you want—"create a scraper for product prices"—and the AI picks the right tool. You lose fine-grained control over every API parameter but gain speed and conversational orchestration for common workflows.
Who on the team should connect the Apify MCP?
Whoever owns your Apify account or has an API key with create/delete permissions. Once connected in Switchy, any workspace member can ask the AI to use those tools, so the key-holder is effectively granting the whole team actor-management rights. If you want tighter control, create a dedicated Apify user with restricted permissions and use that key instead.