Integration

DocumentPro integration

DocumentPro turns documents (PDF, JPEG, PNG, TIFF) into structured JSON with AI extraction Workflows and classifies them into categories. An agent can upload a document of up to 6MB, run an extraction Workflow on it and wait for the extracted JSON, list and read documents, create, read, update and delete extraction Workflows (their field schema), classify an uploaded document against an inline label set or a saved Classifier, and manage Classifiers. The large-file upload (a pre-signed URL the file is PUT to) is not exposed. Authentication is an API key from the DocumentPro app, sent in the x-api-key header.

Connect DocumentPro How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in DocumentPro.Built from the 18 DocumentPro tools below, on the connection you add once.

What you can do with DocumentPro

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Classifier, 5 operations

create_classifierCreate classifierPOSTCreates a reusable Classifier (2+ labels, each optionally mapped to a Workflow). Use it with run_classifier, or as classifier_id in run_extraction to classify and extract at once.
delete_classifierDelete classifierDELETEDeletes a saved Classifier. Irreversible: run_classifier with this id then fails.
get_classifierGet classifierGETGets one saved Classifier: its name and configs (classes with labels and mapped Workflows, model, page range).
list_classifiersList classifiersGETLists the saved Classifiers with their labels and settings. Pass pagination_key to get the next page.
update_classifierUpdate classifierPUTUpdates a saved Classifier. Only the fields sent change; classes, when sent, replaces the whole label list.

Template, 5 operations

create_workflowCreate workflowPOSTCreates an extraction Workflow: a unique template_title, a template_type and the template_schema fields to extract. Returns template_id for run_extraction.
delete_workflowDelete workflowDELETEDeletes an extraction Workflow. Irreversible. Documents it already processed are kept but no longer linked to it.
get_workflowGet workflowGETGets one extraction Workflow: its template_schema fields, parser_config, webhook_url and forwarding email address.
list_workflowsList workflowsGETLists the extraction Workflows in the account, up to 50 per page, with their field schema and forwarding email. Pass pagination_key to get the next page.
update_workflowUpdate workflowPUTUpdates an extraction Workflow. Only the fields sent change: template_type, template_schema, webhook_url, parser_config. The title cannot be changed here.

Document, 3 operations

get_documentGet documentGETGets one uploaded document: file name, page count, source and its parser_runs (each with the request_id to pass to get_extraction_result).
list_documentsList documentsGETLists the documents in the account (default 100) with each one's past extraction runs. Filter by document_id, created_at or search_term.
upload_documentUpload documentPOSTUploads one document (PDF, JPEG, PNG or TIFF, up to 6MB) from a file reference. Returns its document_id: pass it to run_extraction.

Classify, 2 operations

classify_documentClassify documentPOSTClassifies an uploaded document into one of 2+ inline labels (classification_schema). The document must have been through run_extraction first. 1 credit.
run_classifierRun classifierPOSTClassifies an uploaded document with a saved Classifier. The document must have been through run_extraction first. Returns the label and a score per label. 1 credit.

File, 2 operations

delete_extraction_resultDelete extraction resultDELETEDeletes an extraction job and its result data, by request_id. Irreversible.
get_extraction_resultGet extraction resultGETGets an extraction job by request_id: request_status (pending, processing, completed, failed, exception) and, once completed, response_body.result_json_data.

Extraction, 1 operation

run_extractionRun extractionGETRuns an extraction Workflow (template_id) on an uploaded document: returns request_status and response_body.result_json_data, the extracted JSON. Waits for the job and returns the finished result; gives up after 5 minutes.

Use DocumentPro from Claude Code, Cursor or Codex

Connect DocumentPro in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its DocumentPro operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect DocumentPro

Create your workspace
Sign up free. Nothing to install.
Connect DocumentPro once
Add your DocumentPro connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.