automation
Apify MCP Integration for OpenAI Agents SDK
Connect Apify to OpenAI Agents SDK through the local KosmoKrator MCP gateway with scoped tools, credentials, and write policy.
Connect Apify to OpenAI Agents SDK
Attach KosmoKrator integration tools to OpenAI Agents SDK workflows through a local MCP gateway.
Start the KosmoKrator MCP gateway locally and point the OpenAI Agents SDK MCP tool at that process or wrapper. The gateway is local, scoped to this integration, and starts with
--write=deny so OpenAI Agents can inspect read-capable tools without receiving write access by default.
Apify MCP Config for OpenAI Agents SDK
Use headless JSON commands for CI-style execution and MCP for agent tool discovery.
{
"mcpServers": {
"kosmokrator-apify": {
"type": "stdio",
"command": "kosmo",
"args": [
"mcp:serve",
"--integration=apify",
"--write=deny"
]
}
}
} Run the Gateway Manually
kosmokrator mcp:serve --integration=apify --write=deny Why Use KosmoKrator Here
Expose only Apify instead of a broad multi-service tool list.
Reuse credentials already configured for the KosmoKrator CLI and Lua runtime.
Start read-only, then opt into ask or allow for trusted workspaces.
Apify Tools Visible to OpenAI Agents
OpenAI Agents sees stable MCP tool names generated from the Apify integration catalog.
| MCP tool | Source function | Type | Description |
|---|---|---|---|
integration__apify__apify_run_actor | apify.apify_run_actor | Write | Run an Apify actor. Provide the actor ID and input configuration to start a new run. Returns the run details including run ID and status. Use apify_get_run to check progress. |
integration__apify__apify_get_run | apify.apify_get_run | Read | Get details and status of an Apify actor run. Returns the run status (READY, RUNNING, SUCCEEDED, FAILED, ABORTED, TIMING-OUT, TIMED-OUT), output dataset ID, and other metadata. |
integration__apify__apify_list_actors | apify.apify_list_actors | Read | List Apify actors available to the authenticated user. Returns actor names, IDs, descriptions, and versions. Supports pagination with offset and limit. |
integration__apify__apify_get_actor | apify.apify_get_actor | Read | Get details of a specific Apify actor, including its description, input schema, default run options, and available versions. Use this to understand what input an actor requires before running it. |
integration__apify__apify_list_datasets | apify.apify_list_datasets | Read | List Apify datasets accessible to the authenticated user. Returns dataset IDs, names, item counts, and sizes. Supports pagination. |
integration__apify__apify_get_dataset | apify.apify_get_dataset | Read | Get details of a specific Apify dataset, including its item count, size, name, and associated actor run. Use apify_get_dataset_items to retrieve the actual data. |
integration__apify__apify_get_dataset_items | apify.apify_get_dataset_items | Read | Retrieve items from an Apify dataset. Supports JSON, CSV, and other formats. Use this to get the results from completed actor runs. Datasets are referenced by ID from run results. |
integration__apify__apify_list_key_value_stores | apify.apify_list_key_value_stores | Read | List Apify key-value stores accessible to the authenticated user. Key-value stores hold actor outputs like screenshots, PDFs, or JSON results. Supports pagination. |
integration__apify__apify_get_record | apify.apify_get_record | Read | Get a record from an Apify key-value store by its key. Common keys include "OUTPUT" for actor results, "SCREENSHOT" for page screenshots, or custom keys set by actor runs. |
integration__apify__apify_get_current_user | apify.apify_get_current_user | Read | Get the profile of the currently authenticated Apify user. Returns user ID, username, email, plan details, and monthly usage information. |