{ "openapi": "3.0.1", "info": { "title": "MCP Web Scraper Server — AI-Ready Web Scraping via MCP", "description": "Model Context Protocol (MCP) server for web scraping. Provides scrape, extract, search, and link discovery tools via SSE or WebSocket transport. Connect AI agents and LLMs to live web data.", "version": "1.0", "x-build-id": "De3yYiMF5b1F8Sl9W" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~mcp-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-mcp-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/junipr~mcp-web-scraper/runs": { "post": { "operationId": "runs-sync-junipr-mcp-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/junipr~mcp-web-scraper/run-sync": { "post": { "operationId": "run-sync-junipr-mcp-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "transport": { "title": "MCP Transport", "enum": [ "sse", "stdio" ], "type": "string", "description": "Transport protocol for MCP communication. 'sse' uses Server-Sent Events for HTTP-based connections (recommended for Apify deployment). 'stdio' uses standard I/O for local testing.", "default": "sse" }, "defaultRenderJs": { "title": "Default JavaScript Rendering", "type": "boolean", "description": "Default setting for JavaScript rendering in scrape_url calls. Agents can override this per call. Disable to reduce compute costs for static sites.", "default": true }, "maxConcurrentRequests": { "title": "Max Concurrent Requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of simultaneous scraping operations. Higher values improve throughput but increase memory usage.", "default": 5 }, "defaultProxyGroup": { "title": "Default Proxy Group", "enum": [ "DATACENTER", "RESIDENTIAL", "NONE" ], "type": "string", "description": "Default Apify proxy group for scraping requests. RESIDENTIAL provides best success rate. DATACENTER is faster and cheaper. NONE disables proxy.", "default": "RESIDENTIAL" }, "maxPageSizeBytes": { "title": "Max Page Size (bytes)", "minimum": 102400, "maximum": 52428800, "type": "integer", "description": "Maximum page size in bytes. Pages larger than this are truncated. Default is 5MB.", "default": 5242880 }, "defaultTimeout": { "title": "Default Request Timeout (ms)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Default timeout per request in milliseconds. Agents can override this per call.", "default": 30000 }, "enableSearchTool": { "title": "Enable search_web Tool", "type": "boolean", "description": "Enable the search_web MCP tool. Disable to restrict agents to scraping and extraction only.", "default": true }, "rateLimitPerMinute": { "title": "Rate Limit (calls per minute)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Maximum MCP tool calls per minute across all connected clients. Prevents runaway agents from incurring unexpected costs.", "default": 60 }, "allowedDomains": { "title": "Allowed Domains", "type": "array", "description": "If non-empty, agents can only scrape these domains. Useful for enterprise deployments to restrict scope. Leave empty to allow all non-blocked domains.", "items": { "type": "string" }, "default": [] }, "blockedDomains": { "title": "Blocked Domains", "type": "array", "description": "Domains that agents are not allowed to scrape. Prevents SSRF attacks. The defaults block all localhost and internal network addresses.", "items": { "type": "string" }, "default": [ "localhost", "127.0.0.1", "0.0.0.0", "*.internal", "169.254.169.254" ] } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }