Integration

DocuProx integration

DocuProx extracts structured data from document images and PDFs (invoices, receipts, passports, ID cards, contracts). An agent can process one document with a template built in the DocuProx dashboard, or with plain-language prompts and no template, and get the extracted JSON in the same call, or submit an image, PDF or ZIP batch as a background job, poll its status and read its results within 24 hours. Processing spends DocuProx credits, and the results may hold personal data from IDs and passports. Templates, webhooks and API keys are managed only in the dashboard; the binary PUT upload form of process_document, CSV job results, the account-info and PDF-to-image routes are left out. Requests are rate limited per API key over a 60-second window (the default limits are not published). Authentication is a DocuProx API key, sent in the x-auth header.

Connect DocuProx How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in DocuProx.Built from the 6 DocuProx tools below, on the connection you add once.

What you can do with DocuProx

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.

Each badge shows the default agent permission of an endpoint (allowed: an agent calls it without asking; ask first: you are asked before an agent calls it, when the agent or chat asks permission for sensitive actions; never: no agent may call it), which every user can change endpoint by endpoint in their credential settings.

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

Document, 2 operations

process_documentProcess documentPOSTAgents: ask firstExtracts data from one image or PDF with a DocuProx template and returns the extracted JSON in the same call; its shape is set by the template. Uses DocuProx credits. The result may hold personal data from IDs, passports or invoices.
process_document_with_promptsProcess document with promptsPOSTAgents: ask firstExtracts the fields you name in plain-language prompts from one image or PDF, with no template, and returns the extracted JSON in the same call. Uses DocuProx credits. The result may hold personal data.

Api health, 1 operation

check_api_healthCheck api healthGETAgents: ask firstChecks whether the DocuProx API is up. Spends no credits.

Job, 1 operation

submit_processing_jobSubmit processing jobPOSTAgents: ask firstStarts an asynchronous extraction job for an image, a PDF or a ZIP of documents and returns its job_id at once: poll get_job_status until SUCCESS, then read get_job_results. Uses DocuProx credits, deducted by document type.

Job result, 1 operation

get_job_resultsGet job resultsPOSTAgents: ask firstReturns the extracted records of a job whose status is SUCCESS, one record per processed document, shaped by the job's template. Results are deleted 24 hours after the job completes. Records may hold personal data.

Job status, 1 operation

get_job_statusGet job statusGETAgents: ask firstReturns the record of a job from submit_processing_job: job_id, template_id and status. Poll until status is SUCCESS (then call get_job_results) or a failure: FAILED, UNZIP FILE FAILED or PROCESS IMAGE FAILED.

Use DocuProx from Claude Code, Cursor or Codex

Connect DocuProx in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its DocuProx 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 DocuProx

Create your workspace
Sign up free. Nothing to install.
Connect DocuProx once
Add your DocuProx 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.