Connect Extractaai to AI agents

Connect Extractaai to Claude, Codex, Cursor, or other AI agents for your entire team. Metorial security, governance, observability, and gives your team a unified Magic MCP url to connect.

Supported Tools

view_classification

View Classification

Retrieve the details of an existing document classification, including its name, description, and configured document types with their keywords and linked extraction templates.

upload_classification_files

Upload Classification Files

Upload files to an existing classification for automatic categorization. Provide publicly accessible file URLs. Supported formats: PDF, Word (.docx), text, PNG, JPG.

get_credits

Get Credits

Check remaining account credits. Each credit equals one page of document processing.

get_extraction_results

Get Extraction Results

Retrieve extracted data results for a batch of processed files. Returns the extracted fields and values for each file. Optionally filter by a specific file ID.

view_extraction

View Extraction

Retrieve the details of an existing extraction template, including its name, language, processing options, defined fields, and batch information.

update_classification

Update Classification

Update an existing document classification. Modify the name, description, or document types. Only provided parameters will be changed.

upload_extraction_files

Upload Extraction Files

Upload files to an existing extraction for processing. Files are processed in batches. Provide publicly accessible file URLs. Supported formats: PDF, Word (.docx), text, PNG, JPG.

delete_extraction

Delete Extraction

Delete an extraction template, a specific batch within it, or an individual file. Providing only the extraction ID deletes the entire extraction. Adding a batch ID deletes that batch. Adding both batch and file IDs deletes a single file.

create_classification

Create Classification

Create a document classification that automatically categorizes documents into predefined types based on content. Each document type can include keywords for identification and optionally link to an extraction template for automatic data extraction.

get_classification_results

Get Classification Results

Retrieve classification results for a batch of documents. Returns the predicted document type and confidence score for each file. Optionally filter by a specific file ID.

create_extraction

Create Extraction

Create a new extraction template that defines which fields to extract from documents. Supports custom fields with nested structures, language configuration, and processing options like table extraction, OCR for handwritten text, and checkbox detection.

delete_classification

Delete Classification

Delete a document classification and all its associated data.

update_extraction

Update Extraction

Update an existing extraction template. Only the provided parameters will be modified; omitted parameters remain unchanged. Use this to adjust fields, options, language, or name.

More integrations teams use with Extractaai

GitHub

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.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. 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. Subscribe to webhooks for list and library change notifications. Retrieve site properties and search for sites across Microsoft 365.

Salesforce

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. Subscribe to real-time change events via Change Data Capture and Platform Events. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Airtable

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.

Confluence

Create, read, update, and delete pages, blog posts, comments, and attachments in Confluence spaces. Manage spaces, permissions, labels, and content restrictions. Search content using Confluence Query Language (CQL). Upload and download file attachments with versioning. Manage users, groups, and group memberships. Create and manage whiteboards, databases, folders, and templates. View and update inline tasks. Access audit logs. Listen for webhooks on page, blog, comment, attachment, space, label, and user events.

Bitbucket

Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Track issues with the built-in issue tracker. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.

Technical notes for Extractaai

Extract structured data from unstructured documents including PDFs, Word files, text files, and scanned images (PNG, JPG) using AI and OCR. Create and manage extraction templates with custom fields (string, object, array types) to define what data to extract. Upload files for batch processing with options for table extraction, visual/chart detection, handwritten text recognition, checkbox detection, long document handling, PDF page splitting, and specific page range processing. Classify documents into predefined categories with optional automatic extraction. Use pre-built templates for common document types like invoices, receipts, contracts, resumes, bank statements, business cards, and emails. Monitor extraction results via webhooks for processed and edited events. Check remaining account credits for usage tracking. Supports up to 27 languages.

Connect Extractaai to production AI agents

See how Metorial gives Extractaai access the governance, tracing, and security controls teams need.

Frequently asked questions

Common questions about connecting Extractaai to AI agents with Metorial.

  1. Can Metorial connect Extractaai to AI agents?
    Yes. Metorial connects AI agents to Extractaai through a governed integration layer, so teams can use the provider while keeping access controlled and observable.
  2. Metorial is MCP compatible and lets teams expose approved provider tools to MCP-capable agents and clients through a controlled access layer.
  3. Metorial applies policies across users, groups, providers, agents, and individual tools, then records the context around every agent interaction.
  4. Yes. Metorial records provider activity so teams can inspect tool calls, troubleshoot integrations, and give security teams the visibility they need.