Server facts
Apify MCP Server
Project
- Author
- apify
- Repository
- github.com/apify/actors-mcp-server
- Website
- mcp.apify.com
- License
- MIT
- Category
- Search & Web Data
Tech
- Runtime / language
- node
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 11,578
- Last commit
- Data as of
Tags
- Actor Discovery
- Apify
- Automation
- Data Extraction
- Web Scraping
Overview
Apify MCP Server connects assistants to Apify's catalog of Actors for scraping, crawling, and automation. Instead of requiring a separate integration for every website, it loads an Actor's input schema and exposes the operation as an MCP tool. The README gives examples involving social posts, search results, maps contact details, and a web browser designed for retrieval workflows. Assistants can discover suitable Actors as a task develops rather than relying only on a fixed startup selection.
Helper tools cover Actor search and details, execution, run status, logs, datasets, and key-value storage. Documentation search is available alongside those operational tools. The default configuration includes the RAG Web Browser Actor and several helpers, while some run and storage tools are injected automatically when relevant execution capabilities are present. Support for dynamic discovery varies by client, so the usable workflow depends partly on the assistant application.
The README recommends the hosted streamable HTTP service, which supports OAuth and output-schema inference for structured results. A local stdio launch through npx is also documented but does not provide every hosted feature. The previous hosted SSE endpoint has been removed. Standard local access uses an Apify API token; separate hosted payment paths support x402 or Skyfire instead. Actor runs can incur costs, and the payment documentation distinguishes free discovery from paid execution with prepaid balances.
Install & configure
Requirements
- Node.js and npx for the local launch
- An MCP-compatible client
- Apify API token for the documented local configuration
npx @apify/actors-mcp-serverThe command is the local stdio route. The recommended hosted alternative uses streamable HTTP at remote_url and supports OAuth. Do not append /sse; the old SSE endpoint was removed. Hosted output-schema inference is not available in local stdio mode.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"actors-mcp-server": {
"command": "npx",
"args": [
"@apify/actors-mcp-server"
],
"env": {
"APIFY_TOKEN": "<Apify API token for local access>"
}
}
}
}Config file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"actors-mcp-server": {
"command": "npx",
"args": [
"@apify/actors-mcp-server"
],
"env": {
"APIFY_TOKEN": "<Apify API token for local access>"
}
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
{
"servers": {
"actors-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"@apify/actors-mcp-server"
],
"env": {
"APIFY_TOKEN": "<Apify API token for local access>"
}
}
}
}Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"actors-mcp-server": {
"command": "npx",
"args": [
"@apify/actors-mcp-server"
],
"env": {
"APIFY_TOKEN": "<Apify API token for local access>"
}
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"actors-mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"@apify/actors-mcp-server"
],
"env": {
"APIFY_TOKEN": "<Apify API token for local access>"
}
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.
| Tool | What it does |
|---|---|
| search-actors | Find relevant Actors in Apify Store. |
| fetch-actor-details | Inspect an Actor's schemas, documentation, and pricing before execution. |
| call-actor | Run an Actor with its expected input and retrieve results. |
| get-actor-run | Inspect the details of a particular Actor execution. |
| get-dataset-items | Read dataset records with filtering and pagination. |
| get-key-value-store-record | Retrieve a stored value by its key. |
| abort-actor-run | Stop an Actor execution, optionally using graceful cancellation. |
| search-apify-docs | Locate relevant pages in Apify's documentation. |
| fetch-apify-docs | Load an Apify documentation page from its URL. |
| apify--rag-web-browser | Search and browse web sources through the RAG Web Browser Actor. |
| get-actor-run-list | List an Actor's executions with optional status filtering. |
| get-actor-log | Read logs from a particular Actor execution. |
| get-dataset | Inspect metadata for a dataset. |
| get-dataset-schema | Infer a JSON schema from dataset records. |
| get-key-value-store | Inspect metadata for a key-value store. |
| get-key-value-store-keys | Enumerate keys in a selected store. |
| get-dataset-list | List datasets available to the user. |
| get-key-value-store-list | List the user's available key-value stores. |
| add-actor | Experimentally register an Actor as another callable tool. |
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Discover a scraper for a particular website from an assistant.
- Collect social-media or search-result data through an Actor.
- Retrieve completed run results from datasets or key-value storage.
- Search the web and extract page content with the RAG Web Browser Actor.
Strengths
- Exposes a broad Actor catalog through dynamic discovery.
- Combines execution with run, storage, and documentation helpers.
- Hosted OAuth avoids local process setup for supported clients.
Limitations
- Local stdio lacks some hosted features.
- Client support for dynamic tool discovery varies.
- Paid Actor execution needs an account token or a supported funded payment flow.
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.
