Find the Apify Actor, n8n recipe or agent skill for a web-data job, with ready MCP configs.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Ready-to-paste config that adds chosen Actors (or a website's bundle) to an MCP client through Apify's hosted MCP server: Claude Code, Claude Desktop, Cursor, VS Code, ChatGPT, Codex CLI, Gemini CLI or n8n AI Agent, with steps.
Actor ids (owner/name) to include.
Or: a website whose main Actors to bundle, e.g. 'TikTok'.
Optional server name in the config.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http recipe-for-agents https://recipeforagents.com/mcp-server
Ready-to-paste config that adds chosen Actors (or a website's bundle) to an MCP client through Apify's hosted MCP server: Claude Code, Claude Desktop, Cursor, VS Code, ChatGPT, Codex CLI, Gemini CLI or n8n AI Agent, with steps.
| Argument | Type | Description |
|---|---|---|
| actors | array | Actor ids (owner/name) to include. |
| client | string | |
| website | string | Or: a website whose main Actors to bundle, e.g. 'TikTok'. |
| server_name | string | Optional server name in the config. |
{
"type": "object",
"properties": {
"actors": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 10,
"description": "Actor ids (owner/name) to include."
},
"client": {
"enum": [
"all",
"claude-code",
"claude-desktop",
"cursor",
"vscode",
"chatgpt",
"codex",
"gemini-cli",
"n8n-agent"
],
"type": "string",
"default": "all"
},
"website": {
"type": "string",
"maxLength": 80,
"description": "Or: a website whose main Actors to bundle, e.g. 'TikTok'."
},
"server_name": {
"type": "string",
"maxLength": 60,
"description": "Optional server name in the config."
}
},
"additionalProperties": false
}Find step-by-step n8n recipes that move live web data into a destination (Google Sheets, Slack, Notion, HubSpot, email, Discord, webhook, Qdrant) for a task such as 'new Zillow listings to Slack', plus matching use cases and agent skills. Suggests Actors when no recipe fits.
| Argument | Type | Description |
|---|---|---|
| task* | string | What should happen, e.g. 'daily Google Maps leads into a spreadsheet'. |
| limit | integer | |
| destination | string | Optional: where the data should go (Google Sheets, Slack, Notion, HubSpot, Email, Discord, Webhook, Qdrant). |
{
"type": "object",
"required": [
"task"
],
"properties": {
"task": {
"type": "string",
"maxLength": 300,
"description": "What should happen, e.g. 'daily Google Maps leads into a spreadsheet'."
},
"limit": {
"type": "integer",
"default": 5,
"maximum": 10,
"minimum": 1
},
"destination": {
"type": "string",
"maxLength": 40,
"description": "Optional: where the data should go (Google Sheets, Slack, Notion, HubSpot, Email, Discord, Webhook, Qdrant)."
}
},
"additionalProperties": false
}One recipe in full: what it does, the Actor and input it sends, schedule, de-duplication, setup steps, known limits and, with include_workflow=true, the importable n8n workflow JSON (built-in nodes only).
| Argument | Type | Description |
|---|---|---|
| slug* | string | Recipe slug from find_recipe, or the recipe page URL. |
| include_workflow | boolean | Include the n8n workflow JSON (several KB). |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"maxLength": 300,
"description": "Recipe slug from find_recipe, or the recipe page URL."
},
"include_workflow": {
"type": "boolean",
"default": false,
"description": "Include the n8n workflow JSON (several KB)."
}
},
"additionalProperties": false
}Everything published about one catalogue Actor: description, price, required and example input, output fields, MCP URL, configs for Claude Code/Cursor/VS Code/Codex, n8n workflow, SKILL.md and schema files, matching recipes.
| Argument | Type | Description |
|---|---|---|
| id* | string | Actor id owner/name (from search_tools), or its recipeforagents.com or Apify Store URL. |
{
"type": "object",
"required": [
"id"
],
"properties": {
"id": {
"type": "string",
"maxLength": 300,
"description": "Actor id owner/name (from search_tools), or its recipeforagents.com or Apify Store URL."
}
},
"additionalProperties": false
}The catalogue's categories (leads, social, video, products, property, jobs, search, travel, developer utilities) with Actor counts and the main websites in each.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Websites the catalogue covers, with the number of Actors for each, its page and one MCP URL bundling its main Actors. Filter by part of the name or by category.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Part of a website name, e.g. 'google'. |
| category | string |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 50,
"maximum": 200,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 80,
"description": "Part of a website name, e.g. 'google'."
},
"category": {
"enum": [
"leads",
"social",
"video",
"products",
"property",
"jobs",
"search",
"travel",
"dev"
],
"type": "string"
}
},
"additionalProperties": false
}Find Apify Actors (ready-made scrapers and data tools) an agent can call for a kind of web data, e.g. 'LinkedIn company headcount', 'Amazon prices', 'Google Maps leads with email'. Returns the best matches with website, price, output fields, required input, page and scoped MCP URL. Filter by website or category.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | The data you need, in plain words (website, records, fields). |
| website | string | Only Actors for this website, e.g. 'LinkedIn', 'Zillow'. Also returns that website's bundled MCP URL. |
| category | string | Only this category (keys from list_categories). |
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 8,
"maximum": 25,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200,
"description": "The data you need, in plain words (website, records, fields)."
},
"website": {
"type": "string",
"maxLength": 80,
"description": "Only Actors for this website, e.g. 'LinkedIn', 'Zillow'. Also returns that website's bundled MCP URL."
},
"category": {
"enum": [
"leads",
"social",
"video",
"products",
"property",
"jobs",
"search",
"travel",
"dev"
],
"type": "string",
"description": "Only this category (keys from list_categories)."
}
},
"additionalProperties": false
}Sourced fixes for errors when connecting Apify Actors to Claude, Cursor, VS Code, ChatGPT, Codex, Gemini CLI or n8n (401 unauthorized, 408 timeouts, 429, SSE endpoint gone, tools missing, result too large...).
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| client | string | Optional: the client, e.g. 'Cursor'. |
| problem* | string | The error message or symptom. |
{
"type": "object",
"required": [
"problem"
],
"properties": {
"limit": {
"type": "integer",
"default": 3,
"maximum": 6,
"minimum": 1
},
"client": {
"type": "string",
"maxLength": 40,
"description": "Optional: the client, e.g. 'Cursor'."
},
"problem": {
"type": "string",
"maxLength": 300,
"description": "The error message or symptom."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 13, 2026.