stancld/rossum-mcp

Set up a complete document splitting and sorting pipeline with training queues, splitter engine, automated hooks, and intelligent routing:

1. Create three new queues in workspace `1777693` - Air Waybills, Certificates of Origin, Invoices.
2. Set up the schema with a single enum field on each queue with a name Document type (`document_type`).
3. Upload documents from folders air_waybill, certificate_of_origin, invoice in `examples/data/splitting_and_sorting/knowledge` to corresponding queues.
4. Annotate all uploaded documents with a correct Document type, and confirm the annotation.
    - Beware document types are air_waybill, invoice and certificate_of_origin (lower-case, underscores).
    - IMPORTANT: After confirming all annotations, double check, that all are confirmed/exported, and fix those that are not.
5. Create three new queues in workspace `1777693` - Air Waybills Test, Certificates of Origin Test, Invoices Test.
6. Set up the schema with a single enum field on each queue with a name Document type (`document_type`).
7. Create a new engine in organization `1`, with type = 'splitter'.
8. Configure engine training queues to be - Air Waybills, Certificates of Origin, Invoices.
    - DO NOT copy knowledge.
    - Update Engine object.
9. Create a new schema that will be the same as the schema from the queue `3885208`.
10. Create a new queue (with splitting UI feature flag!) with the created engine and schema in the same workspace called: Inbox.
11. Create a python function-based the **`Splitting & Sorting`** hook on the new inbox queue with this settings:
    **Functionality**: Automatically splits multi-document uploads into separate annotations and routes them to appropriate queues.
    Split documents should be routed to the following queues: Air Waybills Test, Certificates of Origin Test, Invoices Test

    **Trigger Events**:
    - annotation_content.initialize (suggests split to user)
    - annotation_content.confirm (performs actual split)
    - annotation_content.export (performs actual split)

    **How it works**: Python code

    **Settings**:
    - sorting_queues: Maps document types to target queue IDs for routing
    - max_blank_page_words: Threshold for blank page detection (pages with fewer words are considered blank)
12. Upload 10 documents from `examples/data/splitting_and_sorting/testing` folder to inbox queues.

What This Demonstrates:

• Queue Orchestration: Creates 7 queues (3 training + 3 test + 1 inbox) with consistent schemas

• Knowledge Warmup: Uploads and annotates 90 training documents to teach the engine

• Splitter Engine: Configures an AI engine to detect document boundaries and types

• Hook Automation: Sets up a sophisticated webhook that automatically:

  • Splits multi-document PDFs into individual annotations
  • Removes blank pages intelligently
  • Routes split documents to correct queues by type
  • Suggests splits on initialization and executes on confirmation

• End-to-End Testing: Validates the entire pipeline with test documents

This example showcases the agent's ability to orchestrate complex workflows involving multiple queues, engines, schemas, automated hooks with custom logic, and intelligent document routing - all from a single conversational prompt.

Automatically analyze and document all hooks/extensions configured on a queue:

Briefly explain the functionality of every hook based on description and/or code one by one for a queue `2042843`.

Store output in extension_explanation.md

What This Does:

• Lists all hooks/extensions on the specified queue
• Analyzes each hook's description and code
• Generates clear, concise explanations of functionality
• Documents trigger events and settings
• Saves comprehensive documentation to a markdown file

This example shows how the agent can analyze existing automation to help teams understand their configured workflows.

Create a new queue, warm it up with training documents, and test automation performance:

1. Create a new queue in the same namespace as queue `3904204`
2. Set up the same schema field as queue `3904204`
3. Update schema so that everything with confidence > 90% will be automated
4. Rename the queue to: MCP Air Waybills
5. Copy the queue knowledge from `3904204`
6. Return the queue status to check the queue status
7. Upload all documents from `examples/data/splitting_and_sorting/knowledge/air_waybill`
   to the new queue
8. Wait until all annotations are processed
9. Finally, return queue URL and an automation rate (exported documents)

Result:

{
  "queue_url": "https://api.elis.rossum.ai/v1/queues/3920572",
  "queue_id": 3920572,
  "queue_name": "MCP Air Waybills",
  "total_documents": 30,
  "exported_documents": 26,
  "to_review_documents": 4,
  "automation_rate_percent": 86.7
}

The agent automatically creates the queue, uploads documents, monitors processing, and calculates automation performance - achieving 86.7% automation rate from just 30 training documents.

• upload_document - Upload documents for AI extraction
• get_annotation - Retrieve extracted data and status
• list_annotations - List all annotations with filtering
• start_annotation - Start annotation for field updates
• bulk_update_annotation_fields - Update field values with JSON Patch
• confirm_annotation - Confirm and finalize annotations

• get_queue - Retrieve queue details
• get_queue_schema - Retrieve queue schema in one call
• get_queue_engine - Get engine information
• create_queue - Create new queues
• update_queue - Configure automation thresholds

• get_schema - Retrieve schema details
• create_schema - Create new schemas
• update_schema - Configure field-level thresholds
• patch_schema - Add, update, or remove individual schema nodes

• get_engine - Retrieve engine details by ID
• list_engines - List all engines with optional filters
• create_engine - Create extraction or splitting engines
• update_engine - Configure learning and training queues
• create_engine_field - Define engine fields and link to schemas
• get_engine_fields - Retrieve engine fields for an engine

• get_hook - Get hook/extension details
• list_hooks - List webhooks and extensions
• create_hook - Create new hooks/extensions
• update_hook - Update existing hook properties
• list_hook_templates - List available hook templates from Rossum Store
• create_hook_from_template - Create hook from a template
• list_hook_logs - List hook execution logs for debugging
• get_rule - Get business rule details
• list_rules - List validation rules

• get_workspace - Retrieve workspace details
• list_workspaces - List all workspaces with filtering
• create_workspace - Create new workspaces

• get_user - Retrieve user details by ID
• list_users - List users with optional filtering
• list_user_roles - List all user roles (permission groups)

• get_relation - Retrieve annotation relation details
• list_relations - List relations (edit, attachment, duplicate)
• get_document_relation - Retrieve document relation details
• list_document_relations - List document relations (export, einvoice)