{ "openapi": "3.0.1", "info": { "title": "PDF Tables to Excel + True PII Redaction (MCP server)", "description": "Deterministic MCP tools for AI agents: extract tables from PDFs, scans and images to XLSX/CSV with every figure read twice and totals reconciled; truly redact personal data from PDFs (text removed, not covered) with a hashed log. No LLM inside.", "version": "0.1", "x-build-id": "eV3kWLfRqHFzKlYbL" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/doubleaigents~pdf-tables-and-true-redaction-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-doubleaigents-pdf-tables-and-true-redaction-mcp", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/doubleaigents~pdf-tables-and-true-redaction-mcp/runs": { "post": { "operationId": "runs-sync-doubleaigents-pdf-tables-and-true-redaction-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/doubleaigents~pdf-tables-and-true-redaction-mcp/run-sync": { "post": { "operationId": "run-sync-doubleaigents-pdf-tables-and-true-redaction-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "operation", "fileUrl" ], "properties": { "operation": { "title": "Operation", "enum": [ "extract_tables", "redact_pdf" ], "type": "string", "description": "extract_tables: tables to XLSX/CSV with a second-pass check. redact_pdf: true redaction with a log.", "default": "extract_tables" }, "fileUrl": { "title": "File URL", "type": "string", "description": "Public http(s) URL of a PDF, PNG, JPG or TIFF (max 50 MB, 500 pages).", "default": "https://www.w3.org/WAI/WCAG21/working-examples/pdf-table/table.pdf" }, "terms": { "title": "Names / terms to redact", "type": "array", "description": "redact_pdf only. Case-insensitive names, addresses, reference numbers.", "default": [], "items": { "type": "string" } }, "types": { "title": "Detectors", "type": "array", "description": "redact_pdf only. Leave empty for all: email, phone_uk, phone_intl, postcode_uk, ni_number, iban, sort_code, account_number, date_of_birth, term.", "default": [], "items": { "type": "string" } }, "check": { "title": "Second-pass check", "type": "boolean", "description": "extract_tables only. Re-read every numeric cell independently and reconcile totals.", "default": true }, "ocrTextLayer": { "title": "Searchable text on rasterised pages", "type": "boolean", "description": "redact_pdf only. Add an OCR text layer to pages that had to be rasterised.", "default": true }, "lang": { "title": "OCR language", "type": "string", "description": "Tesseract language code. The image ships with eng.", "default": "eng" } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }