Give Claude Code live web data

Run claude mcp add --transport http with Apify's MCP URL and the Actors you want in ?tools=, then type /mcp in Claude Code and sign in to Apify. Add --scope user to use it in every project, or commit a .mcp.json so your team gets the same tools.

Method

  1. Run the command in your project folder. Add --scope user to make it available in every project.

    Claude Code config for Google Maps Business Lead Finder with Email & Social Linksterminal or .mcp.json

    Actor on Apify 
    claude mcp add --transport http google-maps-business-lead-finder-with-email "https://mcp.apify.com/?tools=fetch-actor-details,vexaloom-labs/google-maps-business-lead-finder-with-email"

  2. Start Claude Code, type /mcp, pick the server and sign in to Apify in the browser window.

  3. No browser sign-in? Add --header "Authorization: Bearer YOUR_APIFY_TOKEN" to the command instead.

The example uses Google Maps Business Lead Finder with Email & Social Links. Every Actor page and every website page below has the same config, pre-filled.

Apify plugin or a scoped URL?

Apify recommends its own plugin for Claude Code: one install adds the whole Apify MCP server and five Agent Skills, with a sign-in in your browser. The config above is the other route: a URL scoped to the Actors you pick, so Claude Code sees only their tools, which keeps the tool list short and the context small. Use the plugin to explore Apify; use a scoped URL when the agent should do one job with known Actors.

  1. In Claude Code, add the Apify marketplace, install the plugin and reload.
  2. Run /mcp, open plugin:apify:apify, select Enable, then Authenticate and finish the Apify sign-in in your browser.
/plugin marketplace add apify/apify-claude-code-plugin
/plugin install apify@apify
/reload-plugins

From Apify's plugin documentation and Apify's Claude Code guide, checked 2026-11-12. With the Apify CLI, apify mcp install cursor (or another client name) writes the MCP config for you.

Good to know

  • The project scope writes .mcp.json at the repository root; local and user scopes live in ~/.claude.json.
  • In .mcp.json, write the token as ${APIFY_TOKEN} so it is read from the environment instead of being committed.
  • Claude Code's docs mark SSE as deprecated; Apify's /sse endpoint was retired, so use the HTTP transport.

Claude Code configs by website

Each page opens on the Claude Code tab.

When Claude Code does not connect

Why does the client say Unauthorized or invalid token?

Every Apify Actor tool needs a signed-in Apify account. Reconnect the server so the OAuth sign-in runs again, or switch to the token variant: an Authorization: Bearer header with an API token from Apify Console, Settings, API and integrations. For a local server the token must be in the server's own env block, not only in your shell.

Source: Apify MCP server README

Why did my agent's tool list change after an update?

Without a tools parameter Apify's server loads its default tool set, which changes between releases. The URLs on this site pin the tools with ?tools=, so the agent always gets the same Actor tool plus fetch-actor-details. Apify's README gives the same advice for production.

Source: Apify MCP server README

What happens when the agent sends input the Actor rejects?

The server answers with the Actor's input schema, so the agent can fix the arguments and call again. The fetch-actor-details tool in every scoped URL lets it read that schema before the first call.

Source: Apify MCP server README

Claude Code shows Needs authentication. Why?

The server is added but not signed in. Type /mcp in an interactive session and authenticate, or run claude mcp login with the server name. Headless runs with claude -p cannot complete OAuth, so sign in once interactively or use the --header token variant.

Source: Claude Code MCP documentation

Claude Code warns that a tool result is too large. What can I change?

Claude Code warns above 10,000 tokens of tool output and caps it at 25,000 by default (MAX_MCP_OUTPUT_TOKENS raises it). Ask the agent for fewer results per call, for example a lower result limit for the Actor.

Source: Claude Code MCP documentation

My old config uses mcp.apify.com/sse and stopped working. Why?

Apify retired the SSE transport on 1 April 2026. Use https://mcp.apify.com with the streamable HTTP transport, as every config on this site does.

Source: Apify changelog: MCP improvements

Every fix in one place

Questions

Do I need an Apify token for Claude Code?

No, if you sign in: after adding the server, /mcp opens Apify's OAuth flow in your browser. A token header is the alternative for headless machines.

How do I limit the agent to one Actor?

Put only that Actor in the tools parameter, for example ?tools=owner/actor-name. The configs on this site also add fetch-actor-details so the agent can read the input schema first.