MCP Integration

Overview

pdfstork exposes an MCP (Model Context Protocol) server that allows AI assistants like Claude, Cursor, or Windsurf to generate PDFs from your templates through natural language.

Prerequisites

• A pdfstork account with at least one template
• An API token (go to Settings → API Tokens to create one)
• An MCP-compatible AI client

Server endpoint

https://pdfstork.com/mcp/pdf

Authentication uses a Bearer token in the Authorization header.

Configuration

Claude Code (CLI)

Add the server with one command:

claude mcp add --transport http pdfstork https://pdfstork.com/mcp/pdf \
  --header "Authorization: Bearer YOUR_API_TOKEN"

Add --scope user to make it available in all your projects. You can also declare it in the project's .mcp.json, at the repository root:

{
  "mcpServers": {
    "pdfstork": {
      "type": "http",
      "url": "https://pdfstork.com/mcp/pdf",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Claude Desktop

Claude Desktop's configuration file starts local servers only. Connect to pdfstork through the mcp-remote bridge, which runs locally and forwards to the HTTP endpoint (Node.js required). Edit your Claude Desktop configuration file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "pdfstork": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://pdfstork.com/mcp/pdf",
        "--header",
        "Authorization: Bearer YOUR_API_TOKEN"
      ]
    }
  }
}

Restart Claude Desktop after saving the file.

Cursor

Add the server to ~/.cursor/mcp.json for all projects, or to .cursor/mcp.json in a project:

{
  "mcpServers": {
    "pdfstork": {
      "url": "https://pdfstork.com/mcp/pdf",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Windsurf

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "pdfstork": {
      "serverUrl": "https://pdfstork.com/mcp/pdf",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Codex (OpenAI CLI)

Add a section to ~/.codex/config.toml:

[mcp_servers.pdfstork]
url = "https://pdfstork.com/mcp/pdf"
http_headers = { Authorization = "Bearer YOUR_API_TOKEN" }

opencode

Add the server to opencode.json at the project root, or globally in ~/.config/opencode/opencode.json:

{
  "mcp": {
    "pdfstork": {
      "type": "remote",
      "url": "https://pdfstork.com/mcp/pdf",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Available tools

The MCP server provides four tools:

Recommended workflow

1. List templates: call list-templates to see your available templates
2. Inspect a template: call get-template-details with the template ID to understand its variables
3. Generate a PDF: call generate-pdf with the template ID and required data
4. Check usage: call get-usage to monitor your quota

Tool reference

list-templates

No parameters required. Returns an array of templates with id, name and type.

get-template-details

Describes the published version of the template, the one the API renders. Returns id, name, type, variables, sample_data and a hint for the assistant. Each variable has a name, a type, an optional example and, for an array, the item_fields of its rows.

generate-pdf

Returns url, a temporary download link to the PDF, with expires_at and size. The render costs one credit, like any API call.

get-usage

No parameters required. Returns:

• current_month_usage: PDFs generated this month
• quota_limit: your plan's monthly limit
• quota_percentage: usage as a percentage of the quota, rounded to one decimal
• pack_credits: prepaid credits left
• has_quota_remaining: whether you can still generate PDFs, counting prepaid credits
• plan: your current plan (discovery, basic or pro)