From 6dd6260fc9b1cbe02be28fe0d60fb26413eda103 Mon Sep 17 00:00:00 2001 From: Marek Honzal Date: Mon, 21 Sep 2026 11:53:34 +0200 Subject: [PATCH 1/2] docs: align agent onboarding and MCP server pages with the live MCP server and skills --- .../platform/get-started/agent-onboarding.md | 35 +++++-------------- .../integrations/ai/claude/claude-code-cli.md | 2 +- sources/platform/integrations/ai/cursor.md | 2 +- .../platform/integrations/ai/kimi-code-cli.md | 2 +- sources/platform/integrations/ai/manus.md | 6 ++-- sources/platform/integrations/ai/mcp.md | 21 +++-------- .../integrations/ai/openai/codex-app.md | 2 +- .../integrations/ai/openai/codex-cli.md | 2 +- 8 files changed, 21 insertions(+), 51 deletions(-) diff --git a/sources/platform/get-started/agent-onboarding.md b/sources/platform/get-started/agent-onboarding.md index 6597f897b6..b6771de0f0 100644 --- a/sources/platform/get-started/agent-onboarding.md +++ b/sources/platform/get-started/agent-onboarding.md @@ -90,9 +90,12 @@ The pattern is the same across every integration method: pick an Actor, send inp 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/actors-runs-post): -- `memory` (MB) - power of 2, minimum 128. Lower memory means lower cost per second. +- `maxTotalChargeUsd` - cap the total amount charged for the run. Works for all pricing models. +- `maxItems` - cap the number of billed dataset items. Pay-per-result Actors only. - `timeout` (seconds) - cap how long a single run can last. -- `maxTotalChargeUsd` - cap total run cost for pay-per-event Actors. +- `memory` (MB) - power of 2, minimum 128. Lower memory means lower cost per second. + +Over MCP, pass the same caps in the `callOptions` argument of `call-actor`. Never put them in the Actor input, where they are ignored or rejected. See [Usage and resources](/actors/running/usage-and-resources) and [Billing](/account/billing) for details. @@ -117,9 +120,7 @@ The MCP server's `search-actors`, `fetch-actor-details`, and docs tools work wit ::: -#### Remote (recommended) - -Works with Claude Code, Cursor, VS Code, GitHub Copilot, and other remote-capable clients. +Works with Claude Code, Claude Desktop, Cursor, VS Code, GitHub Copilot, and other remote-capable clients. 1. Add the following to your MCP client's configuration: @@ -135,27 +136,7 @@ Works with Claude Code, Cursor, VS Code, GitHub Copilot, and other remote-capabl 1. Restart your client and sign in when prompted. OAuth handles authentication automatically. -#### Local/stdio - -For clients that only support local MCP servers, for example 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" } - } - } - } - ``` - -1. Replace `YOUR_TOKEN` with your API token and restart the client. - -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](/integrations/mcp). +For client-specific steps, use the [MCP Configurator](https://mcp.apify.com), which generates ready-to-paste configs. For a client that supports only local MCP servers, tool selection, and Bearer token authentication, see the [MCP server documentation](/integrations/mcp). ### API client @@ -283,7 +264,7 @@ npx skills add apify/agent-skills | `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 | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code | For the full list and details, see the [skills registry](https://skills.sh/apify/agent-skills). diff --git a/sources/platform/integrations/ai/claude/claude-code-cli.md b/sources/platform/integrations/ai/claude/claude-code-cli.md index a9a2c6ced9..4759b1b30c 100644 --- a/sources/platform/integrations/ai/claude/claude-code-cli.md +++ b/sources/platform/integrations/ai/claude/claude-code-cli.md @@ -100,7 +100,7 @@ The agent searches Apify Store, fetches the top Actor's details through `plugin: | `apify-actor-development` | Full Actor lifecycle - template selection, development, local testing, and deployment with `apify push`. | | `apify-actorization` | Converts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors. | | `apify-generate-output-schema` | Generates dataset and key-value store schemas for existing Actors. | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package. | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code. | Example prompts that route to specific skills: diff --git a/sources/platform/integrations/ai/cursor.md b/sources/platform/integrations/ai/cursor.md index bcf4ce2326..d56d562023 100644 --- a/sources/platform/integrations/ai/cursor.md +++ b/sources/platform/integrations/ai/cursor.md @@ -84,7 +84,7 @@ The agent searches Apify Store, fetches the top Actor's details through the Apif | `apify-actor-development` | Full Actor lifecycle - template selection, development, local testing, and deployment with `apify push`. | | `apify-actorization` | Converts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors. | | `apify-generate-output-schema` | Generates dataset and key-value store schemas for existing Actors. | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package. | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code. | Example prompts that route to specific skills: diff --git a/sources/platform/integrations/ai/kimi-code-cli.md b/sources/platform/integrations/ai/kimi-code-cli.md index 9601aa483c..e36136e9a6 100644 --- a/sources/platform/integrations/ai/kimi-code-cli.md +++ b/sources/platform/integrations/ai/kimi-code-cli.md @@ -92,7 +92,7 @@ The router searches Apify Store, fetches the top Actor's details through the Api | `apify-actor-development` | Full Actor lifecycle - template selection, development, local testing, and deployment with `apify push`. | | `apify-actorization` | Converts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors. | | `apify-generate-output-schema` | Generates dataset and key-value store schemas for existing Actors. | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package. | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code. | Example prompts that route to specific skills: diff --git a/sources/platform/integrations/ai/manus.md b/sources/platform/integrations/ai/manus.md index 22972505ef..4ae40f958d 100644 --- a/sources/platform/integrations/ai/manus.md +++ b/sources/platform/integrations/ai/manus.md @@ -80,11 +80,11 @@ Try asking Manus something like: > "Search for 'best project management tools' on Google and summarize the top 10 results" -Manus will call `search-actors` to find [Google Search Scraper](https://apify.com/apify/google-search-scraper), use `call-actor` to run it, and then `get-actor-output` to retrieve and summarize the results. +Manus will call `search-actors` to find [Google Search Scraper](https://apify.com/apify/google-search-scraper), use `call-actor` to run it, and then `get-dataset-items` to retrieve and summarize the results. ## Configure tools -After connecting, the Apify MCP server exposes a default set of tools for Actor discovery (`search-actors`, `fetch-actor-details`, `call-actor`, `get-actor-output`), web browsing (`apify/rag-web-browser`), and documentation search (`search-apify-docs`, `fetch-apify-docs`). See the [full tool reference](/integrations/mcp#available-tools) for the complete list. +After connecting, the Apify MCP server exposes a default set of tools for Actor discovery (`search-actors`, `fetch-actor-details`, `call-actor`, `get-dataset-items`), web browsing (`apify/rag-web-browser`, `apify/web-fetch`), and documentation search (`search-apify-docs`, `fetch-apify-docs`). See the [full tool reference](/integrations/mcp#available-tools) for the complete list. To control which tools are available, append a `tools=` query parameter to the server URL: @@ -109,7 +109,7 @@ Available skills include: | `apify-actor-development` | Full Actor lifecycle: template selection, development, testing, and deployment | | `apify-actorization` | Converts existing projects into Apify Actors | | `apify-generate-output-schema` | Generates dataset and key-value store schemas from Actor source code | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code | ### Import a skill from GitHub diff --git a/sources/platform/integrations/ai/mcp.md b/sources/platform/integrations/ai/mcp.md index f20a5ac50d..0c0180aa40 100644 --- a/sources/platform/integrations/ai/mcp.md +++ b/sources/platform/integrations/ai/mcp.md @@ -48,19 +48,13 @@ The MCP server intentionally excludes two categories of Actors from search and e Before connecting your AI to Apify, you'll need three things: - _An Apify account_ - Sign up for an Apify account, if you don't have one. -- _Apify API token_ - Get your API token from the **API & Integrations** section in [Apify Console](https://console.apify.com/settings/integrations). This token authorizes the MCP server to run Actors on your behalf. Make sure to keep it secure. +- _Apify API token_ - Only needed for the [local stdio server](#local-stdio) or the Bearer token option. The recommended remote connection signs you in with OAuth instead. Get your token from the **API & Integrations** section in [Apify Console](https://console.apify.com/settings/integrations) and keep it secure. - _MCP client_ - An AI agent or client that supports Model Context Protocol (MCP) This could be Anthropic's Claude for Desktop, a VS Code extension with MCP support, or any application that implements the MCP specification. The [official MCP documentation](https://modelcontextprotocol.io/clients) maintains a list of compatible clients. ## Connect and authorize You can connect to the Apify MCP server in two ways: use our hosted service using [Streamable HTTP with OAuth](#streamable-http-with-oauth-recommended), or run the server locally for development and testing using [local stdio](#local-stdio). -:::caution SSE transport deprecated - -Server-Sent Events (SSE) transport will be removed on April 1, 2026. The Apify MCP server now uses Streamable HTTP, in line with the official MCP specification. Visit [mcp.apify.com](https://mcp.apify.com/) to update your client configuration. - -::: - :::tip Structured output schemas The hosted Apify MCP server at `https://mcp.apify.com` supports _output schema inference_ for structured Actor results. Actor tools automatically include inferred output schemas with field-level type information. This helps AI agents understand the expected result structure before calling an Actor. The local stdio server does not support this feature. @@ -260,7 +254,7 @@ The server will download automatically on first use and connect using your API t ## Tool selection -By default, the MCP server loads essential tools for Actor discovery, documentation search, and the RAG Web Browser Actor. You can customize which tools +By default, the MCP server loads the `actors` and `docs` tool categories plus two Actors, RAG Web Browser and Web Fetch. `call-actor` brings the run and storage tools it needs, so a default session can also poll runs and read dataset items. The remaining tools are opt-in through the `tools` parameter. You can customize which tools are available by adding parameters to the server URL: `https://mcp.apify.com?tools=actors,docs,apify/rag-web-browser` @@ -300,13 +294,15 @@ If the `tools` parameter includes any other tool, or you connect to the default | :--- | :--- | :--- | :--- | | `search-actors` | actors | ✅ | Search for Actors in Apify Store | | `fetch-actor-details` | actors | ✅ | Retrieve detailed information about a specific Actor, including its input and output schema, README (summary when available, full otherwise), and pricing | -| `call-actor`* | actors | ❔ | Call an Actor and get its run results | +| `call-actor` | actors | ✅ | Call an Actor and get its run results | | [`apify/rag-web-browser`](https://apify.com/apify/rag-web-browser) | Actor | ✅ | Browse and extract web data | +| [`apify/web-fetch`](https://apify.com/apify/web-fetch) | Actor | ✅ | Fetch a URL and return its content as Markdown, text, HTML, or links | | `search-apify-docs` | docs | ✅ | Search the Apify documentation for relevant pages | | `fetch-apify-docs` | docs | ✅ | Fetch the full content of an Apify documentation page by its URL | | `get-actor-run` | runs | | Get detailed information about a specific Actor run | | `get-actor-run-list` | runs | | Get a list of an Actor's runs, filterable by status | | `get-actor-log` | runs | | Retrieve the logs for a specific Actor run | +| `abort-actor-run` | runs | | Abort a running Actor run | | `get-dataset` | storage | | Get metadata about a specific dataset | | `get-dataset-items` | storage | | Retrieve items from a dataset with support for filtering and pagination | | `get-dataset-schema` | storage | | Generate a JSON schema from dataset items | @@ -320,13 +316,6 @@ If the `tools` parameter includes any other tool, or you connect to the default | `update-actor-task` | tasks | | Update a task's input, run options, or the display configuration of its landing page | | `publish-actor-task` | tasks | | Publish a task on its public landing page | | `unpublish-actor-task` | tasks | | Unpublish a task from its public landing page | -| `get-actor-output`* | - | ✅ | Retrieve the output from an Actor call which is not included in the output preview of the Actor tool. | - -:::note Retrieving full output - -The `get-actor-output` tool is automatically included with any Actor-related tool, such as `call-actor` or specific Actor tools like `apify-slash-rag-web-browser`. When you call an Actor, you receive an output preview. Depending on the output format and length, the preview may contain the complete output or only a limited version to avoid overwhelming the LLM. To retrieve the full output, use the `get-actor-output` tool with the `datasetId` from the Actor call. This tool supports limit, offset, and field filtering. - -::: #### Find and call any Actor on demand diff --git a/sources/platform/integrations/ai/openai/codex-app.md b/sources/platform/integrations/ai/openai/codex-app.md index ba6b571d03..bdcdbc5f5f 100644 --- a/sources/platform/integrations/ai/openai/codex-app.md +++ b/sources/platform/integrations/ai/openai/codex-app.md @@ -89,7 +89,7 @@ Codex searches Apify Store, fetches the top Actor's details through the `apify` | `apify-actor-development` | Full Actor lifecycle - template selection, development, local testing, and deployment with `apify push`. | | `apify-actorization` | Converts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors. | | `apify-generate-output-schema` | Generates dataset and key-value store schemas for existing Actors. | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package. | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code. | Example prompts that route to specific skills: diff --git a/sources/platform/integrations/ai/openai/codex-cli.md b/sources/platform/integrations/ai/openai/codex-cli.md index 2a73465a47..f6a693fb59 100644 --- a/sources/platform/integrations/ai/openai/codex-cli.md +++ b/sources/platform/integrations/ai/openai/codex-cli.md @@ -87,7 +87,7 @@ It then summarizes the Actor's inputs, pricing, and output - all without running | `apify-actor-development` | Full Actor lifecycle - template selection, development, local testing, and deployment with `apify push`. | | `apify-actorization` | Converts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors. | | `apify-generate-output-schema` | Generates dataset and key-value store schemas for existing Actors. | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package. | +| `apify-integration-development` | Builds an official Apify integration for another product: workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code. | Example prompts that route to specific skills: From 8af0a63d4c91a34ab025855bb2a92cc9add43ac4 Mon Sep 17 00:00:00 2001 From: Marek Honzal Date: Tue, 22 Sep 2026 16:59:21 +0200 Subject: [PATCH 2/2] docs: finish the apify-integration-development skill rename in shared partials --- sources/_partials/_apify-plugin-skill-prompts.mdx | 2 +- sources/_partials/_apify-plugin-skills.mdx | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/sources/_partials/_apify-plugin-skill-prompts.mdx b/sources/_partials/_apify-plugin-skill-prompts.mdx index e9723adacf..d12146bb97 100644 --- a/sources/_partials/_apify-plugin-skill-prompts.mdx +++ b/sources/_partials/_apify-plugin-skill-prompts.mdx @@ -6,6 +6,6 @@ To run `apify-actor-development`: > Create an Apify Actor that accepts a `startUrl` and `maxPages` input, crawls the site, and stores each page title and URL. -To run `apify-sdk-integration`: +To run `apify-integration-development`: > Add Apify to this project. The Node.js API route should run an Actor and return dataset items as JSON. diff --git a/sources/_partials/_apify-plugin-skills.mdx b/sources/_partials/_apify-plugin-skills.mdx index 5015eca9cb..c96641d333 100644 --- a/sources/_partials/_apify-plugin-skills.mdx +++ b/sources/_partials/_apify-plugin-skills.mdx @@ -4,4 +4,4 @@ | `apify-actor-development` | Full Actor lifecycle - template selection, development, local testing, and deployment with `apify push`. | | `apify-actorization` | Converts existing JavaScript, TypeScript, Python, or CLI projects into Apify Actors. | | `apify-generate-output-schema` | Generates dataset and key-value store schemas for existing Actors. | -| `apify-sdk-integration` | Integrates Actor execution into applications using the `apify-client` package. | +| `apify-integration-development` | Builds an official Apify integration for another product - workflow-automation apps, agent plugins, AI framework packages, or `apify-client` application code. |