{ "openapi": "3.0.1", "info": { "title": "PDF MCP Server", "description": "Stateless PDF tools exposed via MCP.\nOpen, split, merge, extract text, fill and flatten forms, and generate PDFs in a single run. Designed for deterministic, auditable document transformations by agents and workflows.", "version": "1.1", "x-build-id": "HeFHcBr9KaCbYYbup" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/constant_quadruped~pdf-mcp-server/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-constant_quadruped-pdf-mcp-server", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/constant_quadruped~pdf-mcp-server/runs": { "post": { "operationId": "runs-sync-constant_quadruped-pdf-mcp-server", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/constant_quadruped~pdf-mcp-server/run-sync": { "post": { "operationId": "run-sync-constant_quadruped-pdf-mcp-server", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "tool": { "title": "Tool", "enum": [ "pdf.open", "pdf.get_metadata", "pdf.render_pages", "pdf.extract_text", "pdf.list_form_fields", "pdf.fill_form_fields", "pdf.flatten_form", "pdf.create_from_html", "pdf.merge", "pdf.split", "pdf.extract_pages", "pdf.ai_extract" ], "type": "string", "description": "Tool to execute" }, "pdfUrl": { "title": "PDF URL", "type": "string", "description": "URL of the PDF to process" }, "pdfBase64": { "title": "PDF Base64", "type": "string", "description": "Base64 encoded PDF (alternative to URL)" }, "documentType": { "title": "Document Type (for AI Extract)", "enum": [ "auto", "invoice", "receipt", "contract", "resume", "w2", "form_1099", "bank_statement" ], "type": "string", "description": "Type of document to extract", "default": "auto" }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key (required for pdf.ai_extract)" }, "openaiModel": { "title": "OpenAI Model", "enum": [ "gpt-4o", "gpt-4o-mini", "gpt-4-turbo" ], "type": "string", "description": "OpenAI model to use for extraction", "default": "gpt-4o" }, "pages": { "title": "Pages", "type": "string", "description": "Pages to process (e.g., '1,2,3' or 'all')" }, "formFields": { "title": "Form Fields (JSON)", "type": "string", "description": "JSON object with field names and values for pdf.fill_form_fields" }, "customFields": { "title": "Custom Fields (JSON)", "type": "string", "description": "Custom extraction schema for pdf.ai_extract" }, "html": { "title": "HTML Content", "type": "string", "description": "HTML content for pdf.create_from_html" }, "htmlUrl": { "title": "HTML URL", "type": "string", "description": "URL to convert to PDF" }, "urls": { "title": "PDF URLs (for merge)", "type": "string", "description": "JSON array of PDF URLs to merge" }, "ranges": { "title": "Page Ranges (for split)", "type": "string", "description": "JSON array of page ranges, e.g., [{\"start\":1,\"end\":5},{\"start\":6,\"end\":10}]" }, "renderDpi": { "title": "Render DPI", "type": "integer", "description": "DPI for page rendering", "default": 150 }, "renderFormat": { "title": "Render Format", "enum": [ "png", "jpeg" ], "type": "string", "description": "Output format for rendered pages", "default": "png" }, "pdfFormat": { "title": "PDF Format", "enum": [ "A4", "Letter", "Legal" ], "type": "string", "description": "Page format for PDF creation", "default": "A4" }, "includeConfidence": { "title": "Include Confidence Scores", "type": "boolean", "description": "Include per-field confidence scores in AI extraction", "default": true } } }, "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 } } } } } } } } } }