From 6e0d37efc4047b7bed717d365574dcdd90b42460 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Olender?= <92638966+TC-MO@users.noreply.github.com> Date: Wed, 13 May 2026 23:33:22 +0200 Subject: [PATCH 1/6] docs: add Apify for AI agents onboarding page Consolidates PRs #2367 and #2369 into one entry point for developers integrating AI agents with Apify. Covers MCP, Agent Skills, client libraries, CLI, and REST API. Wires the page into discovery surfaces: homepage card, AI integrations section card, and a disambiguation tip on the build-with-AI page. Bumps MCP to sidebar position 0 so it remains the top item in AI integrations with onboarding sitting right below. --- .../development/quick-start/build_with_ai.md | 5 +- sources/platform/index.mdx | 5 + .../integrations/ai/agent-onboarding.md | 230 ++++++++++++++++++ sources/platform/integrations/ai/mcp/index.md | 2 +- sources/platform/integrations/index.mdx | 8 +- 5 files changed, 246 insertions(+), 4 deletions(-) create mode 100644 sources/platform/integrations/ai/agent-onboarding.md diff --git a/sources/platform/actors/development/quick-start/build_with_ai.md b/sources/platform/actors/development/quick-start/build_with_ai.md index cc86e96019..948285fb3d 100644 --- a/sources/platform/actors/development/quick-start/build_with_ai.md +++ b/sources/platform/actors/development/quick-start/build_with_ai.md @@ -14,9 +14,10 @@ import TabItem from '@theme/TabItem'; This guide provides best practices for building new Actors or improving existing ones using AI code generation tools by providing the AI agents with the right instructions and context. -:::tip Develop AI agents on Apify +:::tip Different goal? -Looking to build and deploy AI agents as Actors? See [Develop AI agents on Apify](/platform/actors/development/quick-start/develop-ai-agents) for the full stack - templates, sandboxes, LLM access, and monetization. +- _Building and deploying AI agents as Actors on Apify?_ See [Develop AI agents on Apify](/platform/actors/development/quick-start/develop-ai-agents) for the full stack - templates, sandboxes, LLM access, and monetization. +- _Connecting an external AI agent to Apify?_ See [Apify for AI agents](/platform/integrations/agent-onboarding) for MCP, Agent Skills, client libraries, and the REST API. ::: diff --git a/sources/platform/index.mdx b/sources/platform/index.mdx index d0710fb402..c7abf59de1 100644 --- a/sources/platform/index.mdx +++ b/sources/platform/index.mdx @@ -33,6 +33,11 @@ Learn how to run any Actor in Apify Store or create your own. A step-by-step gui desc="Learn everything about web scraping and automation with free courses that will turn you into an expert scraper developer." to="/academy" /> + ## Contents diff --git a/sources/platform/integrations/ai/agent-onboarding.md b/sources/platform/integrations/ai/agent-onboarding.md new file mode 100644 index 0000000000..f357e8adbb --- /dev/null +++ b/sources/platform/integrations/ai/agent-onboarding.md @@ -0,0 +1,230 @@ +--- +title: Apify for AI agents +sidebar_label: AI agents +description: Connect your AI agent to the Apify platform - scrape the web, run Actors, and retrieve structured data via MCP, Agent Skills, client libraries, or the REST API. +sidebar_position: 1 +slug: /integrations/agent-onboarding +toc_max_heading_level: 3 +--- + +import Tabs from '@theme/Tabs'; +import TabItem from '@theme/TabItem'; + +Connect your AI agent or application to Apify - the platform for web scraping, data extraction, and browser automation. The typical agent workflow: find an Actor, run it, get structured data back. + +This page is the entry point for developers integrating AI agents with the Apify platform. It covers how to connect, run Actors, retrieve data, and access documentation programmatically. + +**Core concepts:** + +- **Actors** - Serverless cloud programs that perform scraping, crawling, or automation tasks. Thousands of ready-made Actors are available in [Apify Store](https://apify.com/store). +- **Datasets** - Append-only storage for structured results. Every Actor run creates a default dataset. Export as JSON, CSV, Excel, XML, or RSS. +- **API** - RESTful API at `https://api.apify.com/v2` for all platform operations. Also accessible via [MCP](/platform/integrations/mcp), [CLI](/cli), and client libraries. + +## Prerequisites + +Sign up at [console.apify.com](https://console.apify.com/sign-up) using Google or GitHub. The free plan includes monthly platform usage credits with no credit card required. Get your API token from **[Console > Settings > Integrations](https://console.apify.com/settings/integrations)**. + +:::tip Free exploration + +The MCP server's `search-actors`, `fetch-actor-details`, and docs tools work without authentication. You can browse Actors and documentation without an account. + +::: + +## Choose your integration method + +| Method | Best for | Auth | +| :--- | :--- | :--- | +| [MCP server](#mcp-server) | AI agents and coding assistants | OAuth or API token | +| [Agent Skills](#agent-skills) | Guided scraping workflows and Actor development | API token | +| [API client](#api-client) | Backend apps (JavaScript/Python) | API token | +| [CLI](#cli) | Building and deploying custom Actors | API token | +| [REST API](#rest-api) | Any language, HTTP integrations, no-code tools | API token | + +### MCP server + +The [Apify MCP server](/platform/integrations/mcp) connects your agent to the full Apify platform via the [Model Context Protocol](https://modelcontextprotocol.io/). No local installation needed for remote-capable clients. + +_Remote (recommended)_ - works with Claude Code, Cursor, VS Code, GitHub Copilot, and other remote-capable clients: + +```json +{ + "mcpServers": { + "apify": { + "url": "https://mcp.apify.com" + } + } +} +``` + +OAuth handles authentication automatically - you'll be prompted to sign in on first use. + +_Local/stdio_ - for clients that only support local MCP servers (e.g. Claude Desktop): + +```json +{ + "mcpServers": { + "apify": { + "command": "npx", + "args": ["-y", "@apify/actors-mcp-server"], + "env": { "APIFY_TOKEN": "YOUR_TOKEN" } + } + } +} +``` + +For client-specific setup instructions, use the [MCP Configurator](https://mcp.apify.com) which generates ready-to-paste configs. For advanced options and tool customization, see the full [MCP server documentation](/platform/integrations/mcp). + +### Agent Skills + +Pre-built workflows that guide AI agents through data extraction and Actor development tasks. + +```bash +npx skills add apify/agent-skills +``` + +| Skill | What it does | +| :--- | :--- | +| `apify-ultimate-scraper` | Routes web scraping requests to the right Actor for multi-step data pipelines | +| `apify-actor-development` | Guided workflow for building and deploying custom Actors | +| `apify-actorization` | Converts an existing project into an Apify Actor | +| `apify-generate-output-schema` | Auto-generates output schemas from Actor source code | + +Skills work with Claude Code, Cursor, Gemini CLI, and OpenAI Codex. See the [skills registry](https://skills.sh/apify/agent-skills) for the full list and details. + +### API client + +For integrating Apify into your application code. + +:::warning Package naming + +`apify-client` is the API client for _calling_ Actors. The `apify` package is the SDK for _building_ Actors. For backend integration, install `apify-client`. + +::: + + + + +```bash +npm install apify-client +``` + +```typescript +import { ApifyClient } from 'apify-client'; + +const client = new ApifyClient({ token: process.env.APIFY_TOKEN }); +const run = await client.actor('apify/web-scraper').call({ + startUrls: [{ url: 'https://example.com' }], +}); +const { items } = await client.dataset(run.defaultDatasetId).listItems(); +``` + +Full reference: [JavaScript API client docs](https://docs.apify.com/api/client/js) + + + + +```bash +pip install apify-client +``` + +```python +import os +from apify_client import ApifyClient + +client = ApifyClient(token=os.environ['APIFY_TOKEN']) +run = client.actor('apify/web-scraper').call( + run_input={'startUrls': [{'url': 'https://example.com'}]} +) +items = client.dataset(run['defaultDatasetId']).list_items().items +``` + +Full reference: [Python API client docs](https://docs.apify.com/api/client/python) + + + + +### CLI + +For running Actors and building custom ones from the command line. + +```bash +npm install -g apify-cli # or: brew install apify-cli +apify login # authenticate with your API token + +# Discover Actors +apify actors info apify/web-scraper --readme # get Actor README +apify actors info apify/web-scraper --input # get input schema + +# Run an Actor and get output +apify actors call apify/web-scraper \ + -i '{"startUrls": [{"url": "https://example.com"}]}' \ + --output-dataset + +# Build and deploy custom Actors +apify create my-actor # scaffold (JS/TS/Python) +apify run # test locally +apify push # deploy to Apify cloud +``` + +Full reference: [Apify CLI documentation](/cli). + +### REST API + +For HTTP-native integrations or languages without a dedicated client. Base URL: `https://api.apify.com/v2`. Authenticate with the `Authorization: Bearer YOUR_TOKEN` header. + +_Quick reference:_ + +| Action | Method | Endpoint | +| :--- | :--- | :--- | +| Search Actors in Store | `GET` | `/v2/store` | +| Get Actor details | `GET` | `/v2/acts/{actorId}` | +| Run an Actor | `POST` | `/v2/acts/{actorId}/runs` | +| Run Actor (sync, get results) | `POST` | `/v2/acts/{actorId}/run-sync-get-dataset-items` | +| Get run status | `GET` | `/v2/actor-runs/{runId}` | +| Get dataset items | `GET` | `/v2/datasets/{datasetId}/items` | + +The sync endpoint (`run-sync-get-dataset-items`) runs an Actor and returns results in a single request (waits up to 5 minutes). Use async endpoints for longer runs. + +Full reference: [Apify API v2](/api/v2). + +## Documentation access for agents + +Apify documentation is available in formats optimized for programmatic consumption. + +| Resource | How to access | +| :--- | :--- | +| Specific doc page | Append `.md` to any docs URL (for example, `docs.apify.com/platform/actors.md`) | +| Specific doc page (alt) | Request with `Accept: text/markdown` header | +| Docs index | [docs.apify.com/llms.txt](https://docs.apify.com/llms.txt) | +| Full docs (large) | [docs.apify.com/llms-full.txt](https://docs.apify.com/llms-full.txt) | +| Actor Store pages | Append `.md` to any Apify Store URL | +| MCP docs tools | `search-apify-docs`, `fetch-apify-docs` | + +For targeted lookups, prefer `.md` URLs for specific pages or the MCP docs tools over the full `llms-full.txt` file, which may be truncated by agents with limited context windows. + +## Frequently asked questions + +**Which package: `apify` or `apify-client`?** +`apify-client` is for _calling_ Actors from your app. `apify` is the SDK for _building_ Actors on the Apify platform. These are different packages. + +**Can I use Apify without an account?** +Partially. The MCP server lets you search Actors, read details, and browse docs without authentication. Running Actors requires a free account. + +**How do I find the right Actor?** +Use `search-actors` via MCP, browse [Apify Store](https://apify.com/store), or ask your AI agent. Every Actor has a README with capabilities and input schema. + +**What's the difference between MCP and Agent Skills?** +MCP connects your agent to Apify as a tool provider (search, run, get results). Agent Skills add guided workflows on top - multi-step scraping across platforms, Actor development lifecycle, and more. + +**Can I build my own Actor?** +Yes. Install the [CLI](/cli), run `apify create`, and follow the prompts. Use the `apify-actor-development` skill for a guided workflow. Deploy with `apify push`. + +## Useful resources + +- [MCP server integration](/platform/integrations/mcp) - Tool customization, dynamic Actor discovery, and advanced configuration +- [CLI documentation](/cli) - Complete command reference +- [API reference](/api/v2) - All REST API endpoints +- [API client for JavaScript](https://docs.apify.com/api/client/js) | [for Python](https://docs.apify.com/api/client/python) - Client libraries +- [Storage documentation](/platform/storage) - Datasets, key-value stores, and request queues +- [Build with AI](/platform/actors/development) - Build and deploy your first Actor +- [Framework integrations](./crewai.md) - CrewAI, LangChain, LlamaIndex, and more diff --git a/sources/platform/integrations/ai/mcp/index.md b/sources/platform/integrations/ai/mcp/index.md index 8615c20707..bf248a37e5 100644 --- a/sources/platform/integrations/ai/mcp/index.md +++ b/sources/platform/integrations/ai/mcp/index.md @@ -2,7 +2,7 @@ title: Apify MCP server sidebar_label: MCP server description: Learn how to use the Apify MCP server to integrate Apify's library of Actors into your AI agents or large language model-based applications. -sidebar_position: 1 +sidebar_position: 0 slug: /integrations/mcp toc_max_heading_level: 4 --- diff --git a/sources/platform/integrations/index.mdx b/sources/platform/integrations/index.mdx index ba6fdabc3d..6a37a54800 100644 --- a/sources/platform/integrations/index.mdx +++ b/sources/platform/integrations/index.mdx @@ -171,9 +171,15 @@ The Apify platform integrates with popular ETL and data pipeline services, enabl
If you are working on AI/LLM-related applications, we recommend looking into the many integrations with popular AI/LLM ecosystems. -These integrations allow you to use Apify Actors as tools and data sources. +These integrations allow you to use Apify Actors as tools and data sources. If you are connecting any AI agent to Apify, start with the [Apify for AI agents](/platform/integrations/agent-onboarding) page. + Date: Wed, 13 May 2026 23:47:22 +0200 Subject: [PATCH 2/6] docs: expand agent onboarding with quickstart, cost controls, and webhooks pointer Adds three pieces an agent developer needs but the initial merge missed: - Run-your-first-Actor walkthrough with MCP, JavaScript, and Python tabs - shows the shape of an integration before the comparison table - Cost controls callout naming the four run-limit query parameters (memory, timeout, maxItems, maxTotalChargeUsd) - the most common surprise-bill footgun for autonomous agents - Webhooks pointer for long-running Actors - avoids polling when the sync endpoint times out Also links named endpoints and MCP tools where they were previously bare code spans. --- .../integrations/ai/agent-onboarding.md | 63 ++++++++++++++++++- 1 file changed, 62 insertions(+), 1 deletion(-) diff --git a/sources/platform/integrations/ai/agent-onboarding.md b/sources/platform/integrations/ai/agent-onboarding.md index f357e8adbb..a659b9b6d6 100644 --- a/sources/platform/integrations/ai/agent-onboarding.md +++ b/sources/platform/integrations/ai/agent-onboarding.md @@ -30,6 +30,65 @@ The MCP server's `search-actors`, `fetch-actor-details`, and docs tools work wit ::: +## Run your first Actor + +Every Apify Actor follows the same pattern: send input as JSON, get structured data back. The shortest path through each of the main integration methods, using the agent-optimized [RAG Web Browser](https://apify.com/apify/rag-web-browser) Actor: + + + + +After [connecting the MCP server](#mcp-server) to your AI assistant, ask: + +> Use Apify's RAG Web Browser to find the top 3 pages about Apify documentation, then summarize. + +Your agent calls [`search-actors`](/platform/integrations/mcp#available-tools), [`call-actor`](/platform/integrations/mcp#available-tools), and reads the resulting dataset items - all through MCP, no code required. + + + + +```typescript +import { ApifyClient } from 'apify-client'; + +const client = new ApifyClient({ token: process.env.APIFY_TOKEN }); +const run = await client.actor('apify/rag-web-browser').call({ + query: 'Apify documentation', + maxResults: 3, +}); +const { items } = await client.dataset(run.defaultDatasetId).listItems(); +``` + + + + +```python +import os +from apify_client import ApifyClient + +client = ApifyClient(token=os.environ['APIFY_TOKEN']) +run = client.actor('apify/rag-web-browser').call( + run_input={'query': 'Apify documentation', 'maxResults': 3}, +) +items = client.dataset(run['defaultDatasetId']).list_items().items +``` + + + + +The pattern is the same across every integration method: pick an Actor, send input, receive structured data. Choose the connection method below that fits your stack. + +:::caution Cost controls + +When an agent calls Actors automatically, set run limits to prevent surprise bills. Pass these as query parameters on the [run Actor endpoint](/api/v2/act-runs-post): + +- `memory` (MB) - power of 2, minimum 128. Lower memory means lower cost per second. +- `timeout` (seconds) - cap how long a single run can last. +- `maxItems` - cap billed items for pay-per-result Actors. +- `maxTotalChargeUsd` - cap total run cost for pay-per-event Actors. + +See [Usage and resources](/platform/actors/running/usage-and-resources) and [Billing](/platform/console/billing) for details. + +::: + ## Choose your integration method | Method | Best for | Auth | @@ -183,7 +242,9 @@ _Quick reference:_ | Get run status | `GET` | `/v2/actor-runs/{runId}` | | Get dataset items | `GET` | `/v2/datasets/{datasetId}/items` | -The sync endpoint (`run-sync-get-dataset-items`) runs an Actor and returns results in a single request (waits up to 5 minutes). Use async endpoints for longer runs. +The sync endpoint ([`run-sync-get-dataset-items`](/api/v2/act-run-sync-get-dataset-items-post)) runs an Actor and returns results in a single request (waits up to 5 minutes). Use [async endpoints](/api/v2/act-runs-post) for longer runs. + +For runs that take longer than the sync timeout, prefer [webhooks](/platform/integrations/webhooks) over polling - Apify will POST a notification to your URL when the run finishes, avoiding wasted requests. Full reference: [Apify API v2](/api/v2). From 75ffada144ff519c02609e888e57ab368f0510cc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Olender?= <92638966+TC-MO@users.noreply.github.com> Date: Thu, 14 May 2026 00:17:37 +0200 Subject: [PATCH 3/6] docs: refine agent onboarding per style and taxonomy feedback - Bold reserved for UI elements; non-UI emphasis uses italic - "Sign up to Apify Console" instead of URL or specific OAuth providers - Sample agent prompt as a text code block, not a blockquote - Promote bold/italic-paragraph leads to real headings, with MCP setup rewritten as numbered procedures - Move Agent Skills out of the integration-method comparison into its own section; reframe as a layer on top of MCP or coding assistants - Link each endpoint in the REST quick-reference table to its API doc - Remove maxItems from cost controls (pay-per-result is deprecated) - Dissolve the FAQ - each entry now covered inline or by structure --- .../integrations/ai/agent-onboarding.md | 133 +++++++++--------- 1 file changed, 63 insertions(+), 70 deletions(-) diff --git a/sources/platform/integrations/ai/agent-onboarding.md b/sources/platform/integrations/ai/agent-onboarding.md index a659b9b6d6..694f840ed3 100644 --- a/sources/platform/integrations/ai/agent-onboarding.md +++ b/sources/platform/integrations/ai/agent-onboarding.md @@ -12,17 +12,15 @@ import TabItem from '@theme/TabItem'; Connect your AI agent or application to Apify - the platform for web scraping, data extraction, and browser automation. The typical agent workflow: find an Actor, run it, get structured data back. -This page is the entry point for developers integrating AI agents with the Apify platform. It covers how to connect, run Actors, retrieve data, and access documentation programmatically. +## Core concepts -**Core concepts:** - -- **Actors** - Serverless cloud programs that perform scraping, crawling, or automation tasks. Thousands of ready-made Actors are available in [Apify Store](https://apify.com/store). -- **Datasets** - Append-only storage for structured results. Every Actor run creates a default dataset. Export as JSON, CSV, Excel, XML, or RSS. -- **API** - RESTful API at `https://api.apify.com/v2` for all platform operations. Also accessible via [MCP](/platform/integrations/mcp), [CLI](/cli), and client libraries. +- _Actors_ - Serverless cloud programs that perform scraping, crawling, or automation tasks. Thousands of ready-made Actors are available in [Apify Store](https://apify.com/store). +- _Datasets_ - Append-only storage for structured results. Every Actor run creates a default dataset. Export as JSON, CSV, Excel, XML, or RSS. +- _API_ - RESTful API at `https://api.apify.com/v2` for all platform operations. Also accessible via [MCP](/platform/integrations/mcp), [CLI](/cli), and client libraries. ## Prerequisites -Sign up at [console.apify.com](https://console.apify.com/sign-up) using Google or GitHub. The free plan includes monthly platform usage credits with no credit card required. Get your API token from **[Console > Settings > Integrations](https://console.apify.com/settings/integrations)**. +Sign up to [Apify Console](https://console.apify.com/sign-up). The free plan includes monthly platform usage credits with no credit card required. Get your API token from **[Console > Settings > Integrations](https://console.apify.com/settings/integrations)**. :::tip Free exploration @@ -39,7 +37,9 @@ Every Apify Actor follows the same pattern: send input as JSON, get structured d After [connecting the MCP server](#mcp-server) to your AI assistant, ask: -> Use Apify's RAG Web Browser to find the top 3 pages about Apify documentation, then summarize. +```text +Use Apify's RAG Web Browser to find the top 3 pages about Apify documentation, then summarize. +``` Your agent calls [`search-actors`](/platform/integrations/mcp#available-tools), [`call-actor`](/platform/integrations/mcp#available-tools), and reads the resulting dataset items - all through MCP, no code required. @@ -82,7 +82,6 @@ When an agent calls Actors automatically, set run limits to prevent surprise bil - `memory` (MB) - power of 2, minimum 128. Lower memory means lower cost per second. - `timeout` (seconds) - cap how long a single run can last. -- `maxItems` - cap billed items for pay-per-result Actors. - `maxTotalChargeUsd` - cap total run cost for pay-per-event Actors. See [Usage and resources](/platform/actors/running/usage-and-resources) and [Billing](/platform/console/billing) for details. @@ -94,7 +93,6 @@ See [Usage and resources](/platform/actors/running/usage-and-resources) and [Bil | Method | Best for | Auth | | :--- | :--- | :--- | | [MCP server](#mcp-server) | AI agents and coding assistants | OAuth or API token | -| [Agent Skills](#agent-skills) | Guided scraping workflows and Actor development | API token | | [API client](#api-client) | Backend apps (JavaScript/Python) | API token | | [CLI](#cli) | Building and deploying custom Actors | API token | | [REST API](#rest-api) | Any language, HTTP integrations, no-code tools | API token | @@ -103,52 +101,45 @@ See [Usage and resources](/platform/actors/running/usage-and-resources) and [Bil The [Apify MCP server](/platform/integrations/mcp) connects your agent to the full Apify platform via the [Model Context Protocol](https://modelcontextprotocol.io/). No local installation needed for remote-capable clients. -_Remote (recommended)_ - works with Claude Code, Cursor, VS Code, GitHub Copilot, and other remote-capable clients: - -```json -{ - "mcpServers": { - "apify": { - "url": "https://mcp.apify.com" - } - } -} -``` +#### Remote (recommended) -OAuth handles authentication automatically - you'll be prompted to sign in on first use. +Works with Claude Code, Cursor, VS Code, GitHub Copilot, and other remote-capable clients. -_Local/stdio_ - for clients that only support local MCP servers (e.g. Claude Desktop): +1. Add the following to your MCP client's configuration: -```json -{ - "mcpServers": { - "apify": { - "command": "npx", - "args": ["-y", "@apify/actors-mcp-server"], - "env": { "APIFY_TOKEN": "YOUR_TOKEN" } + ```json + { + "mcpServers": { + "apify": { + "url": "https://mcp.apify.com" + } + } } - } -} -``` + ``` -For client-specific setup instructions, use the [MCP Configurator](https://mcp.apify.com) which generates ready-to-paste configs. For advanced options and tool customization, see the full [MCP server documentation](/platform/integrations/mcp). +1. Restart your client and sign in when prompted. OAuth handles authentication automatically. -### Agent Skills +#### Local/stdio -Pre-built workflows that guide AI agents through data extraction and Actor development tasks. +For clients that only support local MCP servers, for example Claude Desktop. -```bash -npx skills add apify/agent-skills -``` +1. Add the following to your MCP client's configuration: -| Skill | What it does | -| :--- | :--- | -| `apify-ultimate-scraper` | Routes web scraping requests to the right Actor for multi-step data pipelines | -| `apify-actor-development` | Guided workflow for building and deploying custom Actors | -| `apify-actorization` | Converts an existing project into an Apify Actor | -| `apify-generate-output-schema` | Auto-generates output schemas from Actor source code | + ```json + { + "mcpServers": { + "apify": { + "command": "npx", + "args": ["-y", "@apify/actors-mcp-server"], + "env": { "APIFY_TOKEN": "YOUR_TOKEN" } + } + } + } + ``` + +1. Replace `YOUR_TOKEN` with your API token and restart the client. -Skills work with Claude Code, Cursor, Gemini CLI, and OpenAI Codex. See the [skills registry](https://skills.sh/apify/agent-skills) for the full list and details. +For client-specific setup instructions, use the [MCP Configurator](https://mcp.apify.com) which generates ready-to-paste configs. For details, see the [MCP server documentation](/platform/integrations/mcp). ### API client @@ -231,16 +222,16 @@ Full reference: [Apify CLI documentation](/cli). For HTTP-native integrations or languages without a dedicated client. Base URL: `https://api.apify.com/v2`. Authenticate with the `Authorization: Bearer YOUR_TOKEN` header. -_Quick reference:_ +#### Quick reference | Action | Method | Endpoint | | :--- | :--- | :--- | -| Search Actors in Store | `GET` | `/v2/store` | -| Get Actor details | `GET` | `/v2/acts/{actorId}` | -| Run an Actor | `POST` | `/v2/acts/{actorId}/runs` | -| Run Actor (sync, get results) | `POST` | `/v2/acts/{actorId}/run-sync-get-dataset-items` | -| Get run status | `GET` | `/v2/actor-runs/{runId}` | -| Get dataset items | `GET` | `/v2/datasets/{datasetId}/items` | +| [Search Actors in Store](/api/v2/store-get) | `GET` | `/v2/store` | +| [Get Actor details](/api/v2/act-get) | `GET` | `/v2/acts/{actorId}` | +| [Run an Actor](/api/v2/act-runs-post) | `POST` | `/v2/acts/{actorId}/runs` | +| [Run Actor (sync, get results)](/api/v2/act-run-sync-get-dataset-items-post) | `POST` | `/v2/acts/{actorId}/run-sync-get-dataset-items` | +| [Get run status](/api/v2/actor-run-get) | `GET` | `/v2/actor-runs/{runId}` | +| [Get dataset items](/api/v2/dataset-items-get) | `GET` | `/v2/datasets/{datasetId}/items` | The sync endpoint ([`run-sync-get-dataset-items`](/api/v2/act-run-sync-get-dataset-items-post)) runs an Actor and returns results in a single request (waits up to 5 minutes). Use [async endpoints](/api/v2/act-runs-post) for longer runs. @@ -248,6 +239,25 @@ For runs that take longer than the sync timeout, prefer [webhooks](/platform/int Full reference: [Apify API v2](/api/v2). +## Agent Skills + +Once your agent is connected via MCP or a coding assistant, [Apify Agent Skills](https://skills.sh/apify/agent-skills) add pre-built workflows on top - guiding the agent through multi-step scraping pipelines and Actor development tasks. Skills are not a separate integration method; they layer over your existing connection. + +Install into Claude Code, Cursor, Gemini CLI, or OpenAI Codex: + +```bash +npx skills add apify/agent-skills +``` + +| Skill | What it does | +| :--- | :--- | +| `apify-ultimate-scraper` | Routes web scraping requests to the right Actor for multi-step data pipelines | +| `apify-actor-development` | Guided workflow for building and deploying custom Actors | +| `apify-actorization` | Converts an existing project into an Apify Actor | +| `apify-generate-output-schema` | Auto-generates output schemas from Actor source code | + +For the full list and details, see the [skills registry](https://skills.sh/apify/agent-skills). + ## Documentation access for agents Apify documentation is available in formats optimized for programmatic consumption. @@ -263,23 +273,6 @@ Apify documentation is available in formats optimized for programmatic consumpti For targeted lookups, prefer `.md` URLs for specific pages or the MCP docs tools over the full `llms-full.txt` file, which may be truncated by agents with limited context windows. -## Frequently asked questions - -**Which package: `apify` or `apify-client`?** -`apify-client` is for _calling_ Actors from your app. `apify` is the SDK for _building_ Actors on the Apify platform. These are different packages. - -**Can I use Apify without an account?** -Partially. The MCP server lets you search Actors, read details, and browse docs without authentication. Running Actors requires a free account. - -**How do I find the right Actor?** -Use `search-actors` via MCP, browse [Apify Store](https://apify.com/store), or ask your AI agent. Every Actor has a README with capabilities and input schema. - -**What's the difference between MCP and Agent Skills?** -MCP connects your agent to Apify as a tool provider (search, run, get results). Agent Skills add guided workflows on top - multi-step scraping across platforms, Actor development lifecycle, and more. - -**Can I build my own Actor?** -Yes. Install the [CLI](/cli), run `apify create`, and follow the prompts. Use the `apify-actor-development` skill for a guided workflow. Deploy with `apify push`. - ## Useful resources - [MCP server integration](/platform/integrations/mcp) - Tool customization, dynamic Actor discovery, and advanced configuration From 158a8d7d28260caf84cbc17be5644aef8944aca3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Olender?= <92638966+TC-MO@users.noreply.github.com> Date: Thu, 14 May 2026 00:33:13 +0200 Subject: [PATCH 4/6] docs: rename agent onboarding sidebar label to match slug --- sources/platform/integrations/ai/agent-onboarding.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/sources/platform/integrations/ai/agent-onboarding.md b/sources/platform/integrations/ai/agent-onboarding.md index 694f840ed3..e41b649624 100644 --- a/sources/platform/integrations/ai/agent-onboarding.md +++ b/sources/platform/integrations/ai/agent-onboarding.md @@ -1,6 +1,6 @@ --- title: Apify for AI agents -sidebar_label: AI agents +sidebar_label: Agent onboarding description: Connect your AI agent to the Apify platform - scrape the web, run Actors, and retrieve structured data via MCP, Agent Skills, client libraries, or the REST API. sidebar_position: 1 slug: /integrations/agent-onboarding From 8ffe32fd9a62f9723974f40141e88a0ddd4bfabd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Olender?= <92638966+TC-MO@users.noreply.github.com> Date: Thu, 14 May 2026 00:45:05 +0200 Subject: [PATCH 5/6] docs: allow capitalized Serverless in vocab Vocab listed `serverless` as lowercase-only, blocking canonical phrasing at sentence starts. Match the [Ss]torages / [Aa]utoscaling pattern so both cases pass Vale. Restore "Serverless cloud programs" in the agent onboarding bullet. --- .github/styles/config/vocabularies/Docs/accept.txt | 2 +- sources/platform/integrations/ai/agent-onboarding.md | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/.github/styles/config/vocabularies/Docs/accept.txt b/.github/styles/config/vocabularies/Docs/accept.txt index dfb5437af3..aac216fec5 100644 --- a/.github/styles/config/vocabularies/Docs/accept.txt +++ b/.github/styles/config/vocabularies/Docs/accept.txt @@ -7,7 +7,7 @@ CU booleans env npm -serverless +[Ss]erverless [Bb]oolean node_modules [Rr]egex diff --git a/sources/platform/integrations/ai/agent-onboarding.md b/sources/platform/integrations/ai/agent-onboarding.md index e41b649624..17735ffc4d 100644 --- a/sources/platform/integrations/ai/agent-onboarding.md +++ b/sources/platform/integrations/ai/agent-onboarding.md @@ -241,7 +241,7 @@ Full reference: [Apify API v2](/api/v2). ## Agent Skills -Once your agent is connected via MCP or a coding assistant, [Apify Agent Skills](https://skills.sh/apify/agent-skills) add pre-built workflows on top - guiding the agent through multi-step scraping pipelines and Actor development tasks. Skills are not a separate integration method; they layer over your existing connection. +Once you connect an agent via MCP or a coding assistant, [Apify Agent Skills](https://skills.sh/apify/agent-skills) add pre-built workflows on top - guiding the agent through multi-step scraping pipelines and Actor development tasks. Skills are not a separate integration method; they layer over your existing connection. Install into Claude Code, Cursor, Gemini CLI, or OpenAI Codex: @@ -271,7 +271,7 @@ Apify documentation is available in formats optimized for programmatic consumpti | Actor Store pages | Append `.md` to any Apify Store URL | | MCP docs tools | `search-apify-docs`, `fetch-apify-docs` | -For targeted lookups, prefer `.md` URLs for specific pages or the MCP docs tools over the full `llms-full.txt` file, which may be truncated by agents with limited context windows. +For targeted lookups, prefer `.md` URLs for specific pages or the MCP docs tools over the full `llms-full.txt` file. Agents with limited context windows may not load `llms-full.txt` fully. ## Useful resources From 62d4d322ed1111e137e329598deac33e4c5dc292 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Micha=C5=82=20Olender?= <92638966+TC-MO@users.noreply.github.com> Date: Thu, 14 May 2026 13:21:10 +0200 Subject: [PATCH 6/6] docs: address PR feedback on agent onboarding CLI coverage - Add CLI tab to the walkthrough alongside MCP/JS/Python - Lead the install command with curl per CLI README ordering; link to the full install docs for Homebrew/Windows/npm alternatives - Add `apify actors search` to the discovery flow --- .../integrations/ai/agent-onboarding.md | 30 ++++++++++++++++--- 1 file changed, 26 insertions(+), 4 deletions(-) diff --git a/sources/platform/integrations/ai/agent-onboarding.md b/sources/platform/integrations/ai/agent-onboarding.md index 17735ffc4d..7048fbd38b 100644 --- a/sources/platform/integrations/ai/agent-onboarding.md +++ b/sources/platform/integrations/ai/agent-onboarding.md @@ -71,6 +71,16 @@ run = client.actor('apify/rag-web-browser').call( items = client.dataset(run['defaultDatasetId']).list_items().items ``` + + + +```bash +apify login # one-time +apify call apify/rag-web-browser \ + -i '{"query": "Apify documentation", "maxResults": 3}' \ + --output-dataset +``` + @@ -197,20 +207,32 @@ Full reference: [Python API client docs](https://docs.apify.com/api/client/pytho For running Actors and building custom ones from the command line. +Install on macOS or Linux (Windows and Homebrew alternatives in the [CLI install docs](/cli/docs/installation)): + ```bash -npm install -g apify-cli # or: brew install apify-cli +curl -fsSL https://apify.com/install-cli.sh | bash apify login # authenticate with your API token +``` -# Discover Actors +Discover and inspect Actors: + +```bash +apify actors search scraping # search Apify Store apify actors info apify/web-scraper --readme # get Actor README apify actors info apify/web-scraper --input # get input schema +``` + +Run an Actor and get its output: -# Run an Actor and get output +```bash apify actors call apify/web-scraper \ -i '{"startUrls": [{"url": "https://example.com"}]}' \ --output-dataset +``` -# Build and deploy custom Actors +Build and deploy custom Actors: + +```bash apify create my-actor # scaffold (JS/TS/Python) apify run # test locally apify push # deploy to Apify cloud