For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.mcpbundles.com/bundle/apify
Skill page: https://www.mcpbundles.com/skills/apify
Tools: 48
Live probe refreshed Nov 21, 2026 · Endpoint host mcp.mcpbundles.com
AI Skill
SKILL.md
Domain knowledge for Apify — workflow patterns, data models, and gotchas for your AI agent.
Apify
Web scraping and automation platform. Discover scrapers in the Store, run them with custom input, monitor execution, and retrieve structured results.
Entity Hierarchy
Actors (scrapers/automations) are the core unit. Each Actor has a unique id (e.g. apify/web-scraper) and versioned Builds.
Runs are execution instances of an Actor. A run has a status (READY, RUNNING, SUCCEEDED, FAILED, TIMED-OUT, ABORTED) and a defaultDatasetId.
Datasets hold tabular output from runs. Each dataset has paginated Items (the actual scraped data rows).
Key-Value Stores hold arbitrary key→value pairs (JSON, HTML, screenshots). Each run gets a default store. The INPUT key holds the run's input config.
Request Queues manage URL frontier for crawling Actors. Items are URLs with metadata.
Schedules trigger Actor runs on a cron schedule.
Webhooks notify external systems on run state changes.
Capability areas
Store & discovery
Keyword search across the public Actor marketplace yields ids, pricing hints, and popularity—use that before committing to a scraper.
Your Actors vs Store Actors
Owned Actors live in a separate inventory from marketplace listings; open a catalog entry to read README, input schema, and recent run stats.
Execution lifecycle
Runs are started with structured JSON input and return immediately while work continues in the background. Historically completed runs, live status, cancel, resurrect, and advanced “morph” controls all hang off the run object.
Outputs
Tabular datasets expose paginated rows; key-value stores hold blobs like screenshots or HTML snapshots; request queues show crawler frontiers. Each finished run points at its default dataset and default store ids.
Account
Profile reads expose quota consumption and plan ceilings.
Workflows
Find and run a scraper: Marketplace search → inspect Actor metadata and input schema → launch with validated JSON → poll run state until success → pull dataset pages for the result grid.
Monitor active runs: Filter the global run list, open a single run for diagnostics, cancel if it is wedged.
Access run artifacts: Read the run payload for defaultDatasetId vs defaultKeyValueStoreId, then fetch tabular rows or individual store records (e.g. rendered PNGs).
Gotchas
Async execution: Starts return immediately—poll run state until terminal status. Duration ranges from seconds to hours.
Actor ID format: Marketplace Actors use vendor/slug style ids; first-party builds often use opaque hashes.
Dataset pagination: Default page sizes are modest—walk with offset/limit when exports spill past the first window.
Token scope: API tokens are full-account; assume least-privilege operationally even though the vendor does not offer sub-roles.
Run memory: Memory/time drive compute units—compare remaining allowance on the account snapshot when planning big scrapes.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms
Apify
Add to your AI client, then sign in once when you connect.
Apify is a web scraping and automation platform for extracting data from websites at scale. Search the Apify Store for pre-built scrapers (Actors), run them with custom input, monitor runs, and retrieve structured results from datasets.
This listing identifies a third-party integration. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
Apify Abort Run — Abort a running Apify Actor run. Use gracefully=true to let the Actor save partial results before stopping. Returns the updated run object.
Apify Add Queue Req — Add a single URL request to an Apify request queue. The request will be picked up by an Actor crawling from this queue. Use unique_key for deduplication.
Apify Batch Queue Reqs — Add multiple URL requests to an Apify request queue in a single batch call. Up to 10,000 requests per call. Returns counts of processed vs unprocessed requests.
Apify Create Req Queue — Create an Apify request queue. Request queues manage URL crawl queues for Actors. Enqueue URLs on the new queue to feed crawler Actors.
Apify Create Schedule — Create an Apify schedule to automatically run Actors or tasks on a cron schedule. Define the cron expression, timezone, and which Actors/tasks to run.
Apify Create Task — Create a saved Apify Actor task with pre-configured input and options. Tasks let you save common Actor configurations for reuse.
Apify Create Webhook — Create an Apify webhook. Webhooks send HTTP POST requests to your URL when Actor run events occur (succeeded, failed, timed out, etc). Use conditions to target specific Actors or tasks.
Apify Delete Schedule — Delete an Apify schedule. This permanently removes the schedule and stops all future runs.
Apify Delete Task — Delete a saved Apify Actor task. This permanently removes the task configuration.
Apify Delete Webhook — Delete an Apify webhook. This permanently removes the webhook.
Frequently Asked Questions
What is the Apify MCP server?
Apify is a web scraping and automation platform for extracting data from websites at scale. Search the Apify Store for pre-built scrapers (Actors), run them with custom input, monitor runs, and retrieve structured results from datasets. It provides 48 tools that AI agents can use through the Model Context Protocol (MCP).
How do I connect Apify to my AI agent?
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/apify. Authentication is handled automatically.
Apify Del Queue Req — Delete a specific request from an Apify request queue.
Apify Get Actor — Get detailed information about a specific Apify Actor including its name, description, default run configuration (memory, timeout), input schema, stats, and versions. Use the Actor ID from marketplace search or your account inventory.
Apify Get Dataset — Get metadata about a specific Apify dataset including item count, size, creation date, and modification date. Paginate rows to fetch the actual scraped records.
Apify Get Dataset Items — Get items (scraped data) from an Apify dataset. This is how you retrieve results after running an Actor. Pass the defaultDatasetId from the run response. Returns an array of JSON objects — each is one scraped record. Use 'fields' to select specific columns and 'clean' to remove empty items.
Apify Get Dataset Stats — Get statistics for an Apify dataset including item count, data size, field frequencies, and data quality metrics.
Apify Get Dispatch — Get details of a specific Apify webhook dispatch including the request sent, HTTP response received, status, and timing.
Apify Get Kv Record — Get a specific record from an Apify key-value store. Returns the record's content (JSON, text, or binary reference). List store keys first to discover available key names.
Apify Get Kv Store Keys — List keys in an Apify key-value store. Returns key names, sizes, and content types. Common keys include 'INPUT' (run input), 'OUTPUT' (run output), and screenshot keys. Fetch a specific key to read its stored value.
Apify Get Queue Head — Get the next pending requests from the head of an Apify request queue. Returns the URLs that would be processed next by a crawling Actor.
Apify Get Queue Req — Get details of a specific request in an Apify request queue including URL, method, handled status, retry count, and error messages.
Apify Get Req Queue — Get details of an Apify request queue including total, handled, and pending request counts, creation date, and modification date.
Apify Get Run — Get status and details of an Apify Actor run. Returns status (READY, RUNNING, SUCCEEDED, FAILED, ABORTED, TIMED-OUT), timing info, defaultDatasetId (for fetching results), defaultKeyValueStoreId, usage stats, and options. Poll this after starting a run until status is SUCCEEDED or FAILED.
Apify Get Run Log — Get the console log output of an Apify Actor run. Useful for debugging failed runs or monitoring progress. Returns the log as plain text.
Apify Get Schedule — Get details of an Apify schedule including its cron expression, timezone, associated Actors/tasks, enabled status, and next run time.
Apify Get Schedule Log — Get the execution log for an Apify schedule showing when it ran, what actions were triggered, and any errors.
Showing the first 25 tools — full list and schemas: Directory API.
How many tools does Apify provide?
Apify provides 48 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.
What authentication does Apify require?
Apify uses API Key. Apify requires credentials. Connect via MCPBundles and authentication is handled automatically.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.
More in analytics
Other MCP servers in this category from the directory index