{ "service": "docparser", "displayName": "Docparser", "categories": [ "Productivity", "Data" ], "authTypes": [ "api_key" ], "auth": [ { "type": "api_key", "label": "API Key", "placeholder": "Docparser API key", "description": "Docparser API key sent with the api_key header. Open your parser, go to More > Integrations, and copy the parser API key from the official integration settings." } ], "homepageUrl": "https://docparser.com", "actions": [ { "id": "docparser.fetch_document_from_url", "service": "docparser", "name": "fetch_document_from_url", "description": "Queue a publicly accessible document URL for import into a Docparser parser and return the scheduled document metadata.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier to import the document into." }, "url": { "type": "string", "minLength": 1, "description": "The publicly accessible document URL to fetch." }, "remoteId": { "type": "string", "minLength": 1, "description": "An optional passthrough ID that is stored with the fetched document." } }, "additionalProperties": false, "required": [ "parserId", "url" ], "description": "Input parameters for fetching a document into Docparser from a public URL." }, "outputSchema": { "type": "object", "properties": { "documentId": { "type": "string", "description": "The unique identifier of the fetched document." }, "parserId": { "type": "string", "description": "The parser identifier the document was queued against." }, "remoteId": { "anyOf": [ { "type": "string", "description": "The passthrough remote ID returned by Docparser." }, { "type": "null" } ] }, "message": { "type": "string", "description": "The upstream status message, which usually contains a status URL." } }, "additionalProperties": false, "description": "Normalized metadata returned after queuing a URL import in Docparser." } }, { "id": "docparser.get_document_result", "service": "docparser", "name": "get_document_result", "description": "Retrieve the parsed data of one Docparser document. When child documents exist and are included, multiple result rows may be returned.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier that owns the document." }, "documentId": { "type": "string", "minLength": 1, "description": "The unique document identifier returned during import." }, "format": { "type": "string", "enum": [ "object", "flat" ], "description": "The output format for parsed data. `object` returns nested JSON and `flat` returns flattened key/value pairs." }, "includeChildren": { "type": "boolean", "description": "Whether parsed data of child documents should also be returned." } }, "additionalProperties": false, "required": [ "parserId", "documentId" ], "description": "Input parameters for retrieving parsed data of one Docparser document." }, "outputSchema": { "type": "object", "properties": { "results": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string", "description": "The unique identifier of the parsed result." }, "documentId": { "type": "string", "description": "The unique identifier of the source document." }, "remoteId": { "anyOf": [ { "type": "string", "description": "The passthrough remote ID associated with the document." }, { "type": "null" } ] }, "fileName": { "anyOf": [ { "type": "string", "description": "The original file name of the source document." }, { "type": "null" } ] }, "mediaLink": { "anyOf": [ { "type": "string", "description": "The standard Docparser media link for the document." }, { "type": "null" } ] }, "mediaLinkOriginal": { "anyOf": [ { "type": "string", "description": "The original-file media link for the document." }, { "type": "null" } ] }, "mediaLinkData": { "anyOf": [ { "type": "string", "description": "The parsed-data media link for the document." }, { "type": "null" } ] }, "pageCount": { "anyOf": [ { "type": "integer", "description": "The page count of the parsed document." }, { "type": "null" } ] }, "uploadedAt": { "anyOf": [ { "type": "string", "description": "The ISO 8601 timestamp when the document was uploaded." }, { "type": "null" } ] }, "processedAt": { "anyOf": [ { "type": "string", "description": "The ISO 8601 timestamp when the document finished processing." }, { "type": "null" } ] }, "parsedData": { "type": "object", "properties": {}, "additionalProperties": true, "description": "A loose JSON object." }, "raw": { "type": "object", "properties": {}, "additionalProperties": true, "description": "A loose JSON object." } }, "additionalProperties": true, "description": "A normalized parsed-document result returned by Docparser." }, "description": "The parsed result rows returned by Docparser for the requested document." } }, "additionalProperties": false, "description": "The normalized output payload for the get_document_result action." } }, { "id": "docparser.get_document_status", "service": "docparser", "name": "get_document_status", "description": "Retrieve the import, preprocessing, parsing, and webhook-dispatch status of one Docparser document.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier that owns the document." }, "documentId": { "type": "string", "minLength": 1, "description": "The unique document identifier returned during import." } }, "additionalProperties": false, "description": "Input parameters for retrieving a Docparser document status." }, "outputSchema": { "type": "object", "properties": { "status": { "type": "object", "properties": { "token": { "type": "string", "description": "The document token returned by Docparser." }, "remoteId": { "anyOf": [ { "type": "string", "description": "The passthrough remote ID linked to the document." }, { "type": "null" } ] }, "fileSource": { "anyOf": [ { "type": "string", "description": "The import source reported by Docparser, such as `api`." }, { "type": "null" } ] }, "filename": { "anyOf": [ { "type": "string", "description": "The original file name reported by Docparser." }, { "type": "null" } ] }, "mimeType": { "anyOf": [ { "type": "string", "description": "The detected MIME type of the document." }, { "type": "null" } ] }, "pages": { "type": "integer", "description": "The page count reported by Docparser." }, "supported": { "type": "boolean", "description": "Whether the file type is supported by Docparser." }, "importingInProgress": { "type": "boolean", "description": "Whether the document import is still running." }, "processingInProgress": { "type": "boolean", "description": "Whether the parser is still processing the document." }, "webhookDispatchingInProgress": { "type": "boolean", "description": "Whether webhook dispatch is still running." }, "uploadedAt": { "type": "integer", "description": "The Unix timestamp in seconds when the document was uploaded." }, "importedAt": { "type": "integer", "description": "The Unix timestamp in seconds when the document import finished." }, "ocrStartedAt": { "type": "integer", "description": "The Unix timestamp in seconds when OCR started." }, "preprocessedAt": { "type": "integer", "description": "The Unix timestamp in seconds when preprocessing finished." }, "preprocessingInProgressAt": { "type": "integer", "description": "The Unix timestamp in seconds when preprocessing started." }, "processedAt": { "type": "integer", "description": "The Unix timestamp in seconds when parsing completed." }, "firstProcessedAt": { "type": "integer", "description": "The Unix timestamp in seconds when parsing first completed." }, "dispatchedWebhook": { "type": "boolean", "description": "Whether a webhook was dispatched successfully." }, "dispatchedWebhookAt": { "type": "integer", "description": "The Unix timestamp in seconds when the webhook was dispatched." }, "dispatchedWebhookProblem": { "type": "boolean", "description": "Whether webhook dispatch encountered a problem." }, "webhooksCreated": { "type": "integer", "description": "The number of queued webhooks created." }, "webhooksSent": { "type": "integer", "description": "The number of webhooks successfully sent." }, "failedJobs": { "type": "array", "items": { "type": "string", "minLength": 1 }, "description": "The background jobs that failed for this document." }, "raw": { "type": "object", "properties": {}, "additionalProperties": true, "description": "A loose JSON object." } }, "additionalProperties": false, "description": "Normalized status information for a Docparser document." } }, "additionalProperties": false, "description": "The normalized output payload for the get_document_status action." } }, { "id": "docparser.get_multiple_document_results", "service": "docparser", "name": "get_multiple_document_results", "description": "Retrieve parsed data for multiple documents of a specific parser with optional filtering, pagination, queue inclusion, and sorting.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier to read results from." }, "format": { "type": "string", "enum": [ "object", "flat" ], "description": "The output format for parsed data. `object` returns nested JSON and `flat` returns flattened key/value pairs." }, "list": { "type": "string", "enum": [ "last_uploaded", "uploaded_after", "processed_after" ], "description": "The upstream result list mode used to filter which documents are returned." }, "limit": { "type": "integer", "minimum": 1, "maximum": 10000, "description": "The maximum number of result rows to return." }, "date": { "type": "string", "description": "The ISO 8601 or Unix timestamp filter used with `uploaded_after` or `processed_after` list modes." }, "remoteId": { "type": "string", "minLength": 1, "description": "Restrict results to documents with this remote ID." }, "includeProcessingQueue": { "type": "boolean", "description": "Whether in-progress documents should also be included in the result set." }, "sortBy": { "type": "string", "enum": [ "parsed_at", "processed_at", "uploaded_at", "first_processed_at", "imported_at", "integrated_at", "dispatched_webhook_at", "preprocessed_at" ], "description": "The timestamp field used to sort multiple-document results." }, "sortOrder": { "type": "string", "enum": [ "ASC", "DESC" ], "description": "The sort direction used for multiple-document results." } }, "additionalProperties": false, "required": [ "parserId" ], "description": "Input parameters for retrieving parsed data of multiple Docparser documents." }, "outputSchema": { "type": "object", "properties": { "results": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string", "description": "The unique identifier of the parsed result." }, "documentId": { "type": "string", "description": "The unique identifier of the source document." }, "remoteId": { "anyOf": [ { "type": "string", "description": "The passthrough remote ID associated with the document." }, { "type": "null" } ] }, "fileName": { "anyOf": [ { "type": "string", "description": "The original file name of the source document." }, { "type": "null" } ] }, "mediaLink": { "anyOf": [ { "type": "string", "description": "The standard Docparser media link for the document." }, { "type": "null" } ] }, "mediaLinkOriginal": { "anyOf": [ { "type": "string", "description": "The original-file media link for the document." }, { "type": "null" } ] }, "mediaLinkData": { "anyOf": [ { "type": "string", "description": "The parsed-data media link for the document." }, { "type": "null" } ] }, "pageCount": { "anyOf": [ { "type": "integer", "description": "The page count of the parsed document." }, { "type": "null" } ] }, "uploadedAt": { "anyOf": [ { "type": "string", "description": "The ISO 8601 timestamp when the document was uploaded." }, { "type": "null" } ] }, "processedAt": { "anyOf": [ { "type": "string", "description": "The ISO 8601 timestamp when the document finished processing." }, { "type": "null" } ] }, "parsedData": { "type": "object", "properties": {}, "additionalProperties": true, "description": "A loose JSON object." }, "raw": { "type": "object", "properties": {}, "additionalProperties": true, "description": "A loose JSON object." } }, "additionalProperties": true, "description": "A normalized parsed-document result returned by Docparser." }, "description": "The parsed result rows returned by Docparser." } }, "additionalProperties": false, "description": "The normalized output payload for the get_multiple_document_results action." } }, { "id": "docparser.get_parser_models", "service": "docparser", "name": "get_parser_models", "description": "List all model layouts for a specific Docparser parser.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier to list model layouts for." } }, "additionalProperties": false, "description": "Input parameters for retrieving parser model layouts." }, "outputSchema": { "type": "object", "properties": { "models": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string", "description": "The unique identifier of the parser model layout." }, "label": { "type": "string", "description": "The human-readable label of the parser model layout." } }, "additionalProperties": false, "description": "A model layout attached to a specific Docparser parser." }, "description": "The parser model layouts returned by Docparser." } }, "additionalProperties": false, "description": "The normalized parser model list returned by Docparser." } }, { "id": "docparser.list_parsers", "service": "docparser", "name": "list_parsers", "description": "List all Document Parsers linked to the current Docparser account.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": {}, "additionalProperties": false, "description": "No input parameters are required for this action." }, "outputSchema": { "type": "object", "properties": { "parsers": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string", "description": "The unique identifier of the parser." }, "label": { "type": "string", "description": "The human-readable parser label." } }, "additionalProperties": false, "description": "A Document Parser linked to the current Docparser account." }, "description": "The parsers returned by Docparser." } }, "additionalProperties": false, "description": "The normalized parser list returned by Docparser." } }, { "id": "docparser.ping", "service": "docparser", "name": "ping", "description": "Ping the Docparser API to verify that the provided API key is valid.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": {}, "additionalProperties": false, "description": "No input parameters are required for this action." }, "outputSchema": { "type": "object", "properties": { "msg": { "type": "string", "description": "The upstream confirmation message. Docparser returns `pong`." } }, "additionalProperties": false, "description": "The normalized ping response returned by Docparser." } }, { "id": "docparser.reintegrate_documents", "service": "docparser", "name": "reintegrate_documents", "description": "Schedule one or more Docparser documents for the integration queue using their document IDs.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier that owns the documents." }, "documentIds": { "type": "array", "items": { "type": "string", "minLength": 1 }, "description": "The document identifiers to schedule for reintegration.", "minItems": 1 } }, "additionalProperties": false, "description": "Input parameters for scheduling documents for reintegration." }, "outputSchema": { "type": "object", "properties": { "totalReintegrate": { "type": "integer", "description": "The number of documents Docparser scheduled for reintegration." }, "msg": { "anyOf": [ { "type": "string", "description": "The upstream message returned by Docparser." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "The normalized output payload for the reintegrate_documents action." } }, { "id": "docparser.reparse_documents", "service": "docparser", "name": "reparse_documents", "description": "Schedule one or more Docparser documents for re-parsing using their document IDs.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier that owns the documents." }, "documentIds": { "type": "array", "items": { "type": "string", "minLength": 1 }, "description": "The document identifiers to schedule for re-parsing.", "minItems": 1 } }, "additionalProperties": false, "description": "Input parameters for scheduling documents for re-parsing." }, "outputSchema": { "type": "object", "properties": { "totalReparsed": { "type": "integer", "description": "The number of documents Docparser scheduled for re-parsing." }, "msg": { "anyOf": [ { "type": "string", "description": "The upstream message returned by Docparser." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "The normalized output payload for the reparse_documents action." } }, { "id": "docparser.upload_document_by_content", "service": "docparser", "name": "upload_document_by_content", "description": "Upload a document to a Docparser parser by sending base64-encoded file content and an optional file name.", "requiredScopes": [], "providerPermissions": [], "inputSchema": { "type": "object", "properties": { "parserId": { "type": "string", "minLength": 1, "description": "The parser identifier to upload the document to." }, "contentBase64": { "type": "string", "minLength": 1, "description": "The base64-encoded document content to upload." }, "fileName": { "type": "string", "minLength": 1, "description": "The file name to attribute to the uploaded document." }, "remoteId": { "type": "string", "minLength": 1, "description": "An optional passthrough ID that is stored with the document." } }, "additionalProperties": false, "required": [ "parserId", "contentBase64" ], "description": "Input parameters for uploading a document by base64 content." }, "outputSchema": { "type": "object", "properties": { "documentId": { "type": "string", "description": "The unique identifier of the imported document." }, "fileSize": { "anyOf": [ { "type": "integer", "description": "The imported file size in bytes when Docparser returns it." }, { "type": "null" } ] }, "quotaUsed": { "anyOf": [ { "type": "integer", "description": "The amount of account quota consumed by the import." }, { "type": "null" } ] }, "quotaLeft": { "anyOf": [ { "type": "integer", "description": "The remaining account quota after the import." }, { "type": "null" } ] }, "quotaRefill": { "anyOf": [ { "type": "string", "description": "The ISO 8601 timestamp when the account quota refills." }, { "type": "null" } ] } }, "additionalProperties": false, "description": "Normalized import metadata returned after uploading a document to Docparser." } } ] }