Apify MCP integration for AI agents.
Connect AI agents to Apify through 5 structured actions, including get actor, run actor, and get current user. Review authentication, inputs, workflows, and…
- ACTION CONTRACTS
- 5
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Apify integration exposes
The Apify Agent App exposes 5 provider-backed actions for developer tools and data work. Its current contract lets an authorized agent retrieve metadata for one apify actor by identifier, start one apify actor run with an optional json input payload, and retrieve the currently authenticated apify user account. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Apify account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Apify capabilities.
Showing 5 of 5 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
get_actorREADRetrieve metadata for one Apify actor by identifier.
INPUTS: actorId
run_actorWRITEStart one Apify actor run with an optional JSON input payload.
INPUTS: actorId / input / build / memoryMbytes / timeoutSecs
get_current_userREADRetrieve the currently authenticated Apify user account.
get_dataset_itemsREADRetrieve JSON items from one Apify dataset.
INPUTS: datasetId / limit / offset / clean / skipHidden
get_runREADRetrieve the current status and storage identifiers for one Apify actor run.
INPUTS: runId / waitForFinishSeconds
INPUT CONTRACTS
Know what the action needs before it runs.
get_actor
actorIdOPTIONAL- The Apify actor identifier, such as apify~web-scraper or apify/web-scraper.
run_actor
actorIdREQUIRED- The Apify actor identifier, such as apify~web-scraper or apify/web-scraper.
inputOPTIONAL- The JSON input object passed to the actor run.
buildOPTIONAL- The actor build tag or number to run.
memoryMbytesOPTIONAL- The memory limit for the run in megabytes.
timeoutSecsOPTIONAL- The maximum runtime for the run in seconds.
get_dataset_items
datasetIdREQUIRED- The Apify dataset identifier.
limitOPTIONAL- The maximum number of items to return.
offsetOPTIONAL- How many items to skip before returning results.
cleanOPTIONAL- Whether hidden fields and empty values should be removed from each item.
skipHiddenOPTIONAL- Whether fields starting with a hash sign should be skipped.
get_run
runIdREQUIRED- The Apify actor run identifier.
waitForFinishSecondsOPTIONAL- How many seconds to wait for run completion before returning.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect Get Actor
Retrieve metadata for one Apify actor by identifier. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
get_actorControl Run Actor
Start one Apify actor run with an optional JSON input payload. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
run_actorVerify with Get Current User
Retrieve the currently authenticated Apify user account. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
get_current_userSAFETY BOUNDARY
Operate Apify with explicit limits
- Authorize Apify with API key and grant only the provider access required by the selected actions.
- 1 action is change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Apify rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Apify task completed successfully.
CONNECTION MODEL
API key
Apify API token used with the Authorization Bearer header. Create it in Apify Console settings: https://console.apify.com/settings/integrations.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 4
- WRITE SIGNALS
- 1
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Apify.