Apify MCP Server for VS Code: Setup & Config

What you can do with Apify in VS Code

Choose it when assistants need discoverable web-extraction tools backed by Apify Actors.

• Discover a scraper for a particular website from an assistant.
• Retrieve completed run results from datasets or key-value storage.

Before you start: Apify in VS Code

• Node.js and npx for the local launch
• An MCP-compatible client
• Apify API token for the documented local configuration

The 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.

Apify VS Code configuration

1. Choose VS Code configuration scope

   For Apify MCP Server, open Workspace: .vscode/mcp.json. Merge into servers; preserve existing inputs.

2. Add Apify MCP Server to VS Code

   Use the actors-mcp-server entry below in servers. Keep Apify MCP Server's documented stdio connection fields and your other VS Code entries.

3. Check Apify MCP Server in VS Code

   Apify MCP Server: Start in VS Code’s MCP controls; inspect output and trust prompts.

{
  "servers": {
    "actors-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@apify/actors-mcp-server"
      ],
      "env": {
        "APIFY_TOKEN": "<Apify API token for local access>"
      }
    }
  }
}

Apify tools available to VS Code

Apify's stored tool list documents 19 tools; compare it with VS Code's connected tool list, because the stored list is not a live check.

search-actors

Look for search-actors among VS Code's agent-mode tools after starting Apify through the MCP controls.

fetch-actor-details

Look for fetch-actor-details among VS Code's agent-mode tools after starting Apify through the MCP controls.

Inspect an Actor's schemas, documentation, and pricing before execution.

call-actor

Look for call-actor among VS Code's agent-mode tools after starting Apify through the MCP controls.

Run an Actor with its expected input and retrieve results.

get-actor-run

Look for get-actor-run among VS Code's agent-mode tools after starting Apify through the MCP controls.

Inspect the details of a particular Actor execution.

get-dataset-items

Look for get-dataset-items among VS Code's agent-mode tools after starting Apify through the MCP controls.

Read dataset records with filtering and pagination.

get-key-value-store-record

Look for get-key-value-store-record among VS Code's agent-mode tools after starting Apify through the MCP controls.

Retrieve a stored value by its key.

abort-actor-run

Look for abort-actor-run among VS Code's agent-mode tools after starting Apify through the MCP controls.

search-apify-docs

Look for search-apify-docs among VS Code's agent-mode tools after starting Apify through the MCP controls.

fetch-apify-docs

Look for fetch-apify-docs among VS Code's agent-mode tools after starting Apify through the MCP controls.

apify--rag-web-browser

Look for apify--rag-web-browser among VS Code's agent-mode tools after starting Apify through the MCP controls.

get-actor-run-list

Look for get-actor-run-list among VS Code's agent-mode tools after starting Apify through the MCP controls.

List an Actor's executions with optional status filtering.

get-actor-log

Look for get-actor-log among VS Code's agent-mode tools after starting Apify through the MCP controls.

Read logs from a particular Actor execution.

get-dataset

Look for get-dataset among VS Code's agent-mode tools after starting Apify through the MCP controls.

Inspect metadata for a dataset.

get-dataset-schema

Look for get-dataset-schema among VS Code's agent-mode tools after starting Apify through the MCP controls.

Infer a JSON schema from dataset records.

get-key-value-store

Look for get-key-value-store among VS Code's agent-mode tools after starting Apify through the MCP controls.

Inspect metadata for a key-value store.

get-key-value-store-keys

Look for get-key-value-store-keys among VS Code's agent-mode tools after starting Apify through the MCP controls.

get-dataset-list

Look for get-dataset-list among VS Code's agent-mode tools after starting Apify through the MCP controls.

get-key-value-store-list

Look for get-key-value-store-list among VS Code's agent-mode tools after starting Apify through the MCP controls.

add-actor

Look for add-actor among VS Code's agent-mode tools after starting Apify through the MCP controls.

Apify: full stored tool descriptions

Troubleshooting Apify in VS Code

• Make npx @apify/actors-mcp-server (Node.js/npm) available in the workspace, container, or remote environment hosting Apify MCP Server. Start through VS Code's MCP controls; inspect output and trust prompts.
• For Apify MCP Server, keep APIFY_TOKEN out of version control; VS Code documents input variables and secret handling.
• Apify MCP Server uses stdio here: VS Code must keep the configured process running; protocol output belongs on stdout and diagnostics on stderr.
• Known limitation: Local stdio lacks some hosted features.
• Known limitation: Client support for dynamic tool discovery varies.
• Known limitation: Paid Actor execution needs an account token or a supported funded payment flow.
• General VS Code troubleshooting lives in the /clients/vscode guide.

Frequently asked questions