Ask your agent in plain language. Each of these maps to a real tool on the server.
add_document_feedback
Submit corrected field values for a previously extracted document to enable continuous learning. Uses the object ID returned from extraction along with verified field name-value pairs to improve future extraction accuracy. This feedback mechanism allows Typless to learn incrementally from every human validation.
extract_document
Extract structured data from a document file using a configured document type. Submits a document (PDF, JPG, BMP, PNG, TIFF) and returns extracted fields with confidence scores, coordinates, and recognized values. Each field may have up to 5 predicted values ranked by confidence. Dates are normalized to YYYY-MM-DD and numbers to decimal format.
list_document_types
Retrieve all document types configured in your Typless account. Returns each document type's slug, name, field counts, and model information. Use this to discover available document types before extracting data or managing training.
manage_user_profile
Retrieve or update the authenticated user's profile. When called without update fields, returns the current profile. When update fields are provided, updates the profile and returns the updated information. Supports updating first name, last name, and email address.
start_training
Trigger model training for a specific document type. After adding documents to the dataset, use this to build or update the extraction model. Training must complete before the model can be used for accurate data extraction.
get_extraction_result
Poll the legacy receive-result endpoint for an asynchronous document extraction. For submissions from extract_document_async, use get_extraction_data instead. Returns the current processing status and extracted data when available. The status can be one of: PROCESSING, SUCCESS, FAILURE, or EXPIRED (48 hours after completion). Use this after submitting a document for async extraction.
list_pending_extractions
List asynchronous extraction IDs that have finished processing and are ready to retrieve. Includes successful and failed jobs; excludes jobs in progress and expired results.
get_extraction_data
Retrieve processing status and unmodified extraction data from the current JSON API. Includes metadata fields, line items, VAT rates, and any text blocks returned by the provider. Unknown field values remain null.
extract_document_async
Submit a document for asynchronous extraction with the current JSON API. Returns an extraction ID for get_extraction_data. Supports a customer identifier for usage reporting and optional text block parsing.
add_training_document
Add an original document and verified metadata, line item, and VAT rate values to a document type training dataset using the current JSON API. Returns the dataset element identifier reported by Typless.
get_current_user
Retrieve the account email and name associated with the connected API key through the legacy user profile endpoint.
Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.
{"mcpServers": {"metorial": {"url": "<your-magic-mcp-url>"}}}
claude mcp add --transport http metorial <your-magic-mcp-url>
codex mcp add metorial --url <your-magic-mcp-url>codex mcp login metorial
One governed layer for every app your agents reach, not a separate connector per tool.
Create, read, update, and archive pages and databases in a Notion workspace. Manage blocks (paragraphs, lists, headings, embeds, etc.) within pages. Query databases with filters and sorts across rich property types including text, numbers, dates, selects, relations, and formulas. Search across pages and databases by title. Add and read comments on pages and blocks. Upload files to pages. Manage workspace users and retrieve user profiles.
Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.
Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.
Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.
Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.
Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.
Extract structured fields, line items, and VAT rates from business documents with Typless. Submit asynchronous extractions, retrieve completed jobs, and add verified examples to training datasets. Includes legacy extraction, feedback, training, document discovery, and account profile tools.
Common questions about connecting Typless to AI agents with Metorial.
