Integration

PDFops integration

PDFops runs deterministic PDF operations: list a PDF's AcroForm fields with their current values, fill those fields (optionally flattening the result), merge PDFs into one, and draw a US-Letter invoice PDF from structured data, plus read the API key's monthly quota. The same input always gives a byte-identical PDF. Only AcroForm forms are handled (no signature or button fields), each input file is capped at 4 MB and each request at 4.5 MB, and text is drawn in Latin-1 only. Filled forms often hold personal data; PDFops says uploaded PDFs are processed in memory and not stored. Quotas are hard monthly caps: past them every call answers HTTP 429 until the 1st of the next month (UTC). Not exposed: the free-key signup (it emails a key and revokes the previous one) and the service health probe. Authentication is an API key (free key 250 requests a month, paid tiers more) sent in the X-API-Key header; the anonymous per-address trial is not used, since every LiveContext call would share it.

Connect PDFops How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PDFops.Built from the 5 PDFops tools below, on the connection you add once.

What you can do with PDFops

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.

Invoice pdf, 1 operation

generate_invoice_pdfGenerate invoice pdfPOSTAgents: ask firstDraws a US-Letter invoice PDF from data (seller, buyer, 1 to 100 line items, optional number, dates, currency, tax rate, notes) and returns it as a file; totals are computed. Same input gives the same bytes. Latin-1 text only.

Pdf, 1 operation

merge_pdfsMerge pdfsPOSTAgents: ask firstMerges 2 to 10 PDFs into one PDF file, pages in the order pdf_1, pdf_2 and so on; form fields stop being interactive. To merge more, merge the result again with the rest.

Pdf form, 1 operation

fill_pdf_formFill pdf formPOSTAgents: ask firstFills a PDF's AcroForm fields and returns the filled PDF as a file; flatten=true locks the values into the page. Names come from inspect_pdf_fields and every value is a string. Values and output often hold personal data.

Pdf form field, 1 operation

inspect_pdf_fieldsInspect pdf fieldsPOSTAgents: ask firstLists a PDF's AcroForm fields (name, type, current value, options, read-only) and a fillTemplate to edit and pass to fill_pdf_form; call it before filling. No form gives count 0. Current values may hold personal data.

Usage, 1 operation

get_usageGet usageGETAgents: ask firstReturns the API key's monthly quota: tier (free, indie or pro), limit, used, remaining, period and reset time. Calling it consumes no quota; only successful PDF calls count as used.

Use PDFops from Claude Code, Cursor or Codex

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

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