Apify

Video tutorial: Integrate 8,000+ Apify Actors and Agents with Claude

You can use the Apify MCP Server in two ways:

- https://mcp.apify.comstreamable transport

Standard Input/Output (stdio): Ideal for local integrations and command-line tools like the Claude for Desktop client.

- Set the MCP client server command tonpx @apify/actors-mcp-serverand theAPIFY_TOKENenvironment variable to your Apify API token.
- Seenpx @apify/actors-mcp-server --helpfor more options.

Want to try Apify MCP without any setup?

You can pay for Actor runs without an Apify API token usingAGI,direct x402, orSkyfire.

ℹ️Scope:Both direct x402 and Skyfire are limited to Pay Per Event Actors, don't support Standby Actors, and settle per run instead of minting a token.

Actor run costs vary, so both payment methods use a prepaid balance model. The payment flow happens in four steps:
- Discovery: The agent discovers Actors withsearch-actorsorfetch-actor-details. Those calls are free.
- Prepayment: Before running a paid Actor tool, the agent funds a prepaid balance.

- Direct x402:mcpcautomatically signs a $1.00 USDC transaction.
- Skyfire: The agent creates a PAY token (minimum $5.00) using Skyfire'screate-pay-tokentool.

- Direct x402: Handled automatically bymcpcusing the prepaid balance.
- Skyfire: The agent explicitly passes the PAY token in theskyfire-pay-idinput property.

# Create a new wallet mcpc x402 init # Import an existing wallet mcpc x402 import <private-key> # Show the wallet address and a funding QR code, so you can fund it with USDC on Base (https://base.org) mcpc x402

Connect to the server with x402 enabled:

mcpc connect "mcp.apify.com?payment=x402" @apify --x402

mcpc @apify tools-call call-actor actor:="apify/rag-web-browser" input:='{"query": "latest AI news"}'

Configure the Skyfire MCP server and the Apify MCP Server in your client. Addpayment=skyfireto the Apify server URL:

{ "mcpServers": { "skyfire": { "url": "https://api.skyfire.xyz/mcp/sse", "headers": { "skyfire-api-key": "<YOUR_SKYFIRE_API_KEY>" } }, "apify": { "url": "https://mcp.apify.com?payment=skyfire" } } }

The MCP server provides a set of tools for interacting with Apify Actors. Since Apify Store is large and growing rapidly, the MCP server provides a way to dynamically discover and use new Actors.

For example, for theapify/rag-web-browserActor, the input parameters are:

{ "query": "restaurants in San Francisco", "maxResults": 3 }

You don't need to manually specify which Actor to call or its input parameters; the LLM handles this automatically. When a tool is called, the arguments are automatically passed to the Actor by the LLM. You can refer to the specific Actor's documentation for a list of available arguments.

One of the most powerful features of using MCP with Apify is dynamic tool discovery. It allows an AI agent to find new tools (Actors) as needed and incorporate them. Here are some special MCP operations and how the Apify MCP Server supports them:

- Apify Actors: Search for Actors, view their details, and use them as tools for the AI.
- Apify documentation: Search the Apify documentation and fetch specific documents to provide context to the AI.
- Actor runs: Get lists of your Actor runs, inspect their details, and retrieve logs.
- Apify storage: Access data from your datasets and key-value stores.
- Actor tasks: Create, inspect, and update your saved Actor tasks, and publish or unpublish their public landing pages.

Here is an overview list of all the tools provided by the Apify MCP Server.

Legend for theEnabled by defaultcolumn:

- ✅ — in the default tool set.
- ⚡ — auto-injected whencall-actor, an Actor tool, orget-actor-runis present (which is true in the default configuration).
- ✅¹ — served by default, but only when telemetry is enabled and the client is not withheld: Anthropic surfaces (Claude.ai / Claude Desktop / Claude Code) orlocal-agent-mode-apify. To disable, pass an explicittools=list that omits it.

Whencall-actor, an Actor tool, orget-actor-runis present, the server auto-injectsget-actor-run,get-dataset-items,get-key-value-store-record, andabort-actor-run.

When you call an Actor — throughcall-actoror directly via an Actor tool (e.g.,apify--rag-web-browser) — the response contains run metadata, storage IDs, and asummary+nextStep, but no dataset items. To fetch items, follownextStepand callget-dataset-items(auto-injected), passing thedatasetIdreturned from the call.

All tools include metadata annotations to help MCP clients and LLMs understand tool behavior:

- title: Short display name for the tool (e.g., "Search Actors", "Call Actor", "apify/rag-web-browser")
- readOnlyHint:truefor tools that only read data without modifying state (e.g.,get-dataset,fetch-actor-details)
- openWorldHint:truefor tools that access external resources outside the Apify platform (e.g.,call-actorexecutes external Actors). Tools that interact only with the Apify platform (likesearch-actorsorfetch-apify-docs) do not have this hint.

Thetoolsconfiguration parameter is used to specify loaded tools – either categories or specific tools directly, and Apify Actors. For example,tools=storage,runsloads two categories;tools=call-actorloads just one tool.

When no query parameters are provided, the MCP server loads the followingtoolsby default:

If the tools parameter is specified, only the listed tools or categories will be enabled – no default tools will be included.

report-problemis served by default (subject to the gating in the footnote above) but lives in thedevcategory, so an explicittools=devselects it too. To disable it, pass an explicittools=list that omits it (e.g.tools=actors,docs).

The hosted server can be configured using query parameters in the URL. For example, to load the default tools, use:

https://mcp.apify.com?tools=actors,docs,apify/rag-web-browser

For minimal configuration, if you want to use only a single Actor tool - without any discovery or generic calling tools, the server can be configured as follows:

https://mcp.apify.com?tools=apify/my-actor

This setup exposes only the specified Actor (apify/my-actor) as a tool. No other tools will be available.

The CLI can be configured using command-line flags. For example, to load the same tools as in the hosted server configuration, use:

npx @apify/actors-mcp-server --tools actors,docs,apify/rag-web-browser

The minimal configuration is similar to the hosted server configuration:

npx @apify/actors-mcp-server --tools apify/my-actor

As above, this exposes only the specified Actor (apify/my-actor) as a tool. No other tools will be available.

The default tools configuration may change in future versions.When notoolsparameter is specified, the server currently loads default tools, but this behavior is subject to change.

For production use and stable interfaces, always explicitly specify thetoolsparameterto ensure your configuration remains consistent across updates.

Enable UI mode using theuiquery parameter:

You can combine it with other parameters:

https://mcp.apify.com?tools=actors,docs&ui=true

The CLI can be configured using command-line flags. For example, to enable UI mode:

You can also set it via theUI_MODEenvironment variable:

export UI_MODE=true npx @apify/actors-mcp-server