Integration

PDFBolt integration

PDFBolt is a PDF generation API (Chromium rendering). An agent can turn an HTTPS web page, Base64-encoded HTML or a published Handlebars template filled with JSON data into a PDF, returned as a file, as a temporary download link (kept 24 hours) or delivered later to a webhook, with page format, margins, headers and footers, waits, compression and print-production options, check the plan's remaining conversions, and manage reusable templates (list, read, validate, preview, compare, save drafts, publish, delete). Each successful PDF uses document credits (1 per PDF; on paid plans each started 5 MB counts as one); the free plan gives 50 a month, 2 MB per PDF. Not included: options that carry credentials or session data (HTTP basic credentials, cookies, extra request headers, webhook headers). Authentication: the conversion API key from the PDFBolt dashboard (API Credentials page), sent as the API-KEY header; template tools also need a Personal Access Token from the same page, sent as PERSONAL-ACCESS-TOKEN.

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PDFBolt.Built from the 14 PDFBolt tools below, on the connection you add once.

What you can do with PDFBolt

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.

Template, 9 operations

  • compare_templateCompare templatePOSTAgents: ask firstRenders a template's published version (before) and the payload you send (after) as two PDFs to compare, without saving. Billed: each side that renders uses document credits. Needs a published version and the Personal Access Token.
  • create_templateCreate templatePOSTAgents: ask firstCreates a new template and its first draft (not yet usable for conversions: publish_template does that). The whole draft is validated; no PDF is rendered and no credits are used. Returns templateId and the draft version.
  • delete_templateDelete templateDELETEAgents: ask firstDELETES a whole template (draft and published versions) for good: there is no restore, and conversions can no longer use its templateId. Already generated PDFs are kept. Needs the Personal Access Token; uses no credits.
  • get_templateGet templateGETAgents: ask firstReturns one template: name, description, Base64 HTML content, sample data, PDF parameters and version info. Content comes from the active draft when there is one, else from the published version. Needs the Personal Access Token.
  • list_templatesList templatesGETAgents: ask firstLists your team's templates, newest first (not paged): id, name, description, engine, whether a draft exists, and the published and draft version numbers and dates. Needs the Personal Access Token.
  • preview_templatePreview templatePOSTAgents: ask firstRenders a template payload to a PDF without saving it and returns a temporary documentUrl, its expiry and size. Billed: each successful preview uses document credits. Needs the Personal Access Token.
  • publish_templatePublish templatePOSTAgents: ask firstPUBLISHES a template's active draft: from then on conversions that pass this templateId render the new version. Wait for any update_template call to finish first. Needs the Personal Access Token; uses no credits.
  • update_templateUpdate templatePOSTAgents: ask firstUpdates an existing template's draft (made from the published version when there is none): only the fields you pass change. Not live until publish_template. Validated, no PDF rendered, no credits used.
  • validate_templateValidate templatePOSTAgents: ask firstChecks a template payload without saving or rendering it (no credits): required fields, Base64 content, size limits, Handlebars syntax and the PDF parameters. Answers with no body when valid; an error lists the problems.

Pdf, 3 operations

  • generate_pdfGenerate pdfPOSTAgents: ask firstGenerates a PDF and returns it as a stored file in one call (billed: uses document credits). Pass exactly one source: url, html (Base64) or templateId with templateData. Use generate_pdf_link for a download link instead.
  • generate_pdf_asyncGenerate pdf asyncPOSTAgents: ask firstQueues a PDF generation and returns a requestId at once; the result is POSTed later to your HTTPS webhook (paid plans; billed on success). Pass exactly one source: url, html (Base64) or templateId with templateData.
  • generate_pdf_linkGenerate pdf linkPOSTAgents: ask firstGenerates a PDF and returns a temporary download URL (kept 24 hours), its size and conversion time (billed: uses document credits). Pass exactly one source: url, html (Base64) or templateId with templateData.

Template contract, 1 operation

  • get_template_contractGet template contractGETAgents: ask firstReturns PDFBolt's public Template Contract: the rules for writing templates (payload fields, HTML and CSS guidance, Handlebars helpers, default options, limits, errors, recommended workflow). Read it before create_template.

Usage, 1 operation

  • get_usageGet usageGETAgents: ask firstReturns your PDFBolt plan and conversion balance: recurring conversions for the billing period (total, left, expiry, overage) and one-time packages (total, left, expiry). Free: does not use credits.

Use PDFBolt from Claude Code, Cursor or Codex

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

  1. Create your workspace

    Sign up free. Nothing to install.

  2. Connect PDFBolt once

    Add your PDFBolt connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.

  3. 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.

PDFBolt integration FAQ

What can you do with the PDFBolt integration?

LiveContext exposes 14 operations on PDFBolt, covering template, pdf, template contract and usage.

Popular integrations

Browse the whole catalog