# AlgoDocs MCP MCP > AlgoDocs provides professional document extraction orchestration via MCP. Send your agent PDFs, images, and Word documents for high-accuracy JSON data parsing. It lets you list active AI extractors, check account usage statistics, monitor processing status, and manage entire folder hierarchies from a single chat interface. ## Overview - **Category:** artificial-intelligence - **Price:** Free - **Tags:** ocr, data-extraction, pdf-parsing, automation, invoice-processing, machine-learning ## Description This MCP connects automated document handling to your AI client. You can upload or link documents—whether they're receipts, invoices, or complex reports—and have the system automatically parse them into structured JSON data. The agent manages the whole ingestion pipeline through natural conversation, letting you monitor status and audit results as they come in. It goes beyond simple uploads; you can list available extractors to ensure the right ruleset is applied before running a document. You also get visibility into your process flow by listing folder details or checking API usage statistics, keeping everything organized within your Vinkius catalog connection. It handles data from public URLs and Base64 strings with high accuracy. This setup means finance teams can automate parsing thousands of invoices without manual input. Data specialists convert scanned PDFs and images into usable JSON right in the chat window. ## Tools ### get_my_account Verifies the current status and credentials of your AlgoDocs account. ### list_extractors Lists all the active, configured AI extraction models available in your account. ### list_folders Shows an overview of all top-level storage folders you have set up. ### upload_document_from_url Initiates extraction by parsing a document directly from a provided public URL. ### get_document_data Pulls the structured JSON data that was extracted from a specific document. ### list_extractor_data Retrieves bulk JSON results from multiple document extractions run by a specific extractor. ### get_document_status Checks if a document processing job is finished or what stage it's at. ### get_folder_details Gets metadata about a specific folder in your document storage structure. ### get_api_usage Retrieves your account details and current API usage statistics. ### list_recent_documents Provides a list of the most recently processed documents in your account. ## Prompt Examples **Prompt:** ``` List all extractors in my AlgoDocs account. ``` **Response:** ``` I've retrieved your extractors. You have 4 active models: 'Invoice_Parser_V2', 'Receipt_Scanner', 'HR_Resumes', and 'Shipping_Labels'. Which one would you like to use for your next document? ``` **Prompt:** ``` Parse this invoice URL: https://example.com/inv.pdf using extractor ID 'ext_123'. ``` **Response:** ``` I've started the extraction for the document at that URL using extractor ext_123. The unique document identifier is 'doc_98765'. I'll monitor the status and notify you as soon as the structured JSON is ready. ``` **Prompt:** ``` Show the extracted data for document ID 'doc_98765'. ``` **Response:** ``` I've retrieved the data for document doc_98765. It contains an invoice for $1,250.00 from 'Global Supplies', dated March 15th, 2026. All 5 line items have been correctly identified. Would you like the full JSON payload? ``` ## Capabilities ### Parse Documents by URL or Upload Submit a public web link or file data to initiate structured JSON extraction from any document type. ### Manage Extraction Models List and retrieve details for all available AI extractors to verify the correct rule set is in place. ### Audit Extracted Data Results Retrieve structured JSON data for specific documents, or pull bulk results from entire sets of extracted files. ### Check Processing Status and Accounts Monitor document processing status using a unique ID, or retrieve overall account usage metrics directly in the chat. ### Organize Document Projects List and audit your folder hierarchy to keep track of different document processing projects. ## Use Cases ### Handling a month's worth of receipts Instead of downloading 50 different PDF receipts and manually entering the total, you ask your agent: 'Use the Receipt_Scanner on these URLs.' The system starts the job, and when you check `get_document_status`, it confirms readiness. Then, calling `get_document_data` provides all the totals in one JSON block. ### Reviewing compliance records You need to see if your new HR document parser is working correctly. You first run `list_extractors`, confirm 'HR_Resumes' is active, and then use it across a batch of test files. Finally, you call `list_extractor_data` to audit all the resulting JSON records for consistency. ### Migrating data from multiple sources Your team has documents stored in various folders (e.g., 'Q1 Invoices', 'Q2 Receipts'). You use `list_folders` to map the structure, then process batches by calling `upload_document_from_url` for each key source link. ### Troubleshooting a stalled workflow A critical document fails to parse. Instead of guessing, you first use `list_recent_documents` to find the ID, then immediately call `get_document_status` to see if the failure was due to an invalid extractor or a bad file format. ## Benefits - Process documents via URLs or uploads. Use `upload_document_from_url` to ingest files instantly without needing a manual transfer step. - Manage all your parsing rulesets using `list_extractors`. You can confirm which models are active before running expensive jobs. - Audit results in bulk. The `list_extractor_data` tool lets you pull JSON data for dozens of documents at once, instead of checking them one by one. - Keep track of everything with folder management tools. Use `list_folders` and `get_folder_details` to maintain a clear organizational structure. - Monitor workflows in real time. If you need to know if an extraction is done, use `get_document_status`. It’s crucial for automation. - Maintain operational visibility by checking usage stats. The `get_api_usage` tool provides quick access to your billing and quota limits. ## How It Works The bottom line is you talk to your agent in plain English, and it executes complex document processing workflows using the underlying APIs. 1. Subscribe to this MCP and provide your AlgoDocs API Key and email credentials. 2. Initiate the process by requesting an action, like parsing a file or listing available extractors, through any compatible AI client. 3. The system returns structured data (JSON), status updates, or a list of resources directly into your chat thread. ## Frequently Asked Questions **How do I see how much API usage I've used with the AlgoDocs MCP?** You use `get_api_usage` to retrieve your account details and current API consumption. This lets you monitor quotas directly in the chat interface. **Can I parse a document that is only available via a web link using AlgoDocs MCP?** Yes, use `upload_document_from_url` to initiate parsing of documents linked from public URLs. You don't have to download the file first. **What should I do if my document extraction fails? Do I need to check the status?** Check the processing state using `get_document_status`. This function tells you if the job is still running, failed, or if it's ready for data retrieval. **Do I have to list all my folders every time I work with AlgoDocs MCP?** No. You can use `list_folders` only when you need an overview of your project structure. Most daily tasks involve simply uploading new documents. **How do I use the `get_my_account` tool to check my subscription status or account limits?** The `get_my_account` tool provides a quick overview of your connection. It lets you confirm if your API key is active and shows essential billing details, so you know exactly when your access expires. **When should I use the `list_extractor_data` tool instead of checking individual documents?** Use `list_extractor_data` when you need to grab results from a large batch of files at once. It's designed for bulk retrieval, letting you pull structured JSON data for many documents simultaneously. **What is the best way to review my processing history using the `list_recent_documents` tool?** The `list_recent_documents` tool pulls up a list of your most recently processed files. This lets you quickly verify which documents have been uploaded and what their unique IDs are without digging through folders. **If I suspect an extractor rule set is wrong, how do I check available models with `list_extractors`?** The `list_extractors` tool shows every active model and ruleset you have configured. This lets you verify the exact names and versions of your AI extractors before running a new document. **How do I find my AlgoDocs API Key?** Log in to AlgoDocs, go to your **Account Settings**, and you will find your API key there. You will need this along with your registered email for authentication. **What is an 'Extractor' in AlgoDocs?** An Extractor is a set of rules and AI models configured to pull specific fields from a certain type of document (e.g., an Invoice Extractor). You must specify an `extractor_id` when uploading documents. **Can I retrieve data from a previously processed document?** Yes! Use the `get_document_data` tool and provide the unique `document_id`. Your agent will retrieve the extracted structured data from AlgoDocs storage.