Integration

PrintFriendly integration

PrintFriendly turns a web page, raw HTML or Markdown into a clean, ad-free PDF or Word (docx) file, or into Markdown, HTML, structured JSON (title, author, date, word count, article HTML and Markdown) or plain text. Convert while you wait (up to 27 seconds), or start a background job for slow pages (up to 55 seconds, optional signed webhook) and read it back, and check a key's usage for the period. Each successful conversion uses one document of the plan (free plan: 100 a month, a footer line on PDF and HTML output, 10 requests a minute; paid plans: 120 requests a minute); failed calls are free, and PDF and Word links expire after 48 hours. The query-string twin of convert and the older per-format create routes, which convert replaces, are not exposed. Authentication is an API key from the API key page of a PrintFriendly account, sent in the X-API-Key header.

Connect PrintFriendly How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in PrintFriendly.Built from the 4 PrintFriendly tools below, on the connection you add once.

What you can do with PrintFriendly

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.

Conversion job, 2 operations

get_conversion_jobGet conversion jobGETAgents: ask firstReads a background conversion by job_id: status queued or processing (look again in a few seconds), succeeded (result holds the converted output) or failed (error holds code, message and retryable). Uses no document.
start_conversion_jobStart conversion jobPOSTAgents: ask firstStarts a background conversion (up to 55 seconds) of a web page, HTML or Markdown and returns its job_id at once; read the result with get_conversion_job. An optional webhook_url receives the finished job. One plan document on success.

Document, 1 operation

convert_documentConvert documentPOSTAgents: ask firstConverts a web page (url), HTML or Markdown into a PDF or Word file (file_url, valid 48 hours) or into Markdown, HTML, JSON or plain text returned inline. Waits up to 27 seconds. Each success uses one plan document.

Usage, 1 operation

get_usageGet usageGETAgents: ask firstChecks that the API key works and returns its plan (free or paid) and the documents used, included and remaining this period. Uses no document.

Use PrintFriendly from Claude Code, Cursor or Codex

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

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