Use Cases
MCP Native

AI-First PDF Generation

Give your AI agents the power to generate documents. Native Model Context Protocol support for Claude, GPT, and any MCP-compatible framework.

Connect in 30 Seconds MCP Integration Guide
MCP Native Protocol
<1s Generation Time
∞ LLM Frameworks

Supported AI Platforms

Works with any LLM that supports tool use

MCP Native

Claude

Anthropic's Claude with native MCP support for tool use

  • Native MCP protocol support
  • Context-aware document generation
  • Structured output handling
  • Multi-turn conversations
Function Calling

OpenAI GPT

GPT-4 and GPT-3.5 with function calling for PDF generation

  • Function calling API
  • JSON mode for structured data
  • Vision for document analysis
  • Assistants API compatible
Flexible

Custom Agents

Build your own AI agents with pdf-mcp as a core tool

  • LangChain integration
  • AutoGPT compatible
  • CrewAI support
  • Any LLM framework

What is Model Context Protocol?

MCP is an open protocol that enables AI models to securely interact with external tools and data sources. Think of it as a standardized way for AI agents to use APIs and services.

  • Secure by Design Sandboxed tool execution with explicit permissions
  • Standardized Interface One protocol works across all compatible LLMs
  • Real-time Execution Tools execute during conversation, not after
mcp-protocol.log

> TOOL_CALL generate_pdf

> INPUT { html: "<h1>Report</h1>..." }

> EXECUTING pdf-mcp API call...

> SUCCESS PDF generated (156KB)

> OUTPUT { url: "https://..." }

> COMPLETE Tool result returned to LLM

What Agents Can Build

Real-world applications for AI-powered document generation

Conversational Document Generation

Let users request documents in natural language. Your AI agent understands the request, gathers data, and generates professional PDFs on demand.

Input User: "Create an invoice for project X"
Output Agent generates formatted PDF invoice with all details
RAG Pipeline Documents

Generate summary documents from retrieved context. Perfect for research assistants that compile findings into downloadable reports.

Input Agent retrieves relevant documents from vector DB
Output Compile findings into formatted PDF report
Multi-Agent Workflows

Use pdf-mcp as a shared tool across multiple AI agents. One agent researches, another analyzes, and a third generates the final document.

Input Research agent completes analysis
Output Documentation agent creates final PDF deliverable
Customer Support Documents

AI agents can generate personalized documentation, troubleshooting guides, or case summaries as PDFs during support interactions.

Input Support ticket requires documentation
Output Generate personalized PDF guide for customer
Automated Reporting

AI agents that monitor systems or analyze data can automatically generate periodic PDF reports with insights and recommendations.

Input Scheduled analysis or threshold alert
Output Generate PDF report with findings and charts
Contract & Proposal Generation

Sales AI agents can create customized proposals and contracts based on conversation context and customer requirements.

Input Customer requirements captured in conversation
Output Generate tailored proposal PDF with pricing

How It Works

Add PDF generation to your agent in 4 steps

1

Get Your API Key

Sign up and receive your API key instantly. 100 free credits coupon on signup.

2

Configure MCP Tool

Add pdf-mcp as a tool in your agent's configuration or system prompt.

3

Define Tool Schema

Register the tool with proper input/output schemas for your LLM.

4

Generate Documents

Your agent can now generate PDFs whenever needed during conversations.

Integration Examples

Copy-paste configurations for your AI framework

MCP Tool Schema

tool-schema.json 
// MCP Tool Definition for pdf-mcp
{
  "name": "generate_pdf",
  "description": "Generate a PDF document from HTML content",
  "input_schema": {
    "type": "object",
    "properties": {
      "html": {
        "type": "string",
        "description": "HTML content to render as PDF"
      },
      "filename": {
        "type": "string",
        "description": "Suggested filename for the PDF"
      },
      "options": {
        "type": "object",
        "properties": {
          "format": { "type": "string", "enum": ["A4", "Letter"] },
          "landscape": { "type": "boolean" }
        }
      }
    },
    "required": ["html"]
  }
}

Claude Desktop

claude_desktop_config.json 
# Claude Desktop MCP Configuration
# Add to ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "pdf-mcp": {
      "command": "npx",
      "args": ["-y", "@anthropic/mcp-server-pdf"],
      "env": {
        "PDF_MCP_API_KEY": "your-api-key-here"
      }
    }
  }
}

LangChain Python

agent.py 
from langchain.tools import Tool
from langchain.agents import AgentExecutor
import requests

def generate_pdf(html: str, options: dict = None) -> dict:
    """Generate PDF from HTML using pdf-mcp API"""
    response = requests.post(
        "https://api.pdf-mcp.io/htmlToPdf",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json"
        },
        json={"html": html, "options": options or {}}
    )
    return response.json()

pdf_tool = Tool(
    name="generate_pdf",
    description="Generate a PDF document from HTML content",
    func=lambda x: generate_pdf(x)
)

# Add to your agent's tools
agent = AgentExecutor(tools=[pdf_tool, ...])

For OpenAI function calling, AutoGPT, CrewAI, and other frameworks, see our complete integration documentation.

Perfect for RAG Pipelines

Retrieval-Augmented Generation workflows often need to produce final documents from retrieved context. pdf-mcp fits naturally into this pattern.

1. Retrieve Query vector database for relevant documents
2. Augment LLM synthesizes findings with context
3. Generate pdf-mcp renders final document as PDF
rag-pipeline.log

[14:32:01] RETRIEVE Querying vector DB...

[14:32:02] FOUND 12 relevant documents

[14:32:03] AUGMENT Sending to LLM with context

[14:32:08] SYNTHESIZE Generating report content...

[14:32:09] GENERATE Calling pdf-mcp API

[14:32:10] COMPLETE research-report.pdf ready

Why Use pdf-mcp for AI?

  • Built for LLMs Designed from the ground up for AI agent workflows
  • Sub-Second Generation Fast enough for real-time conversational use
  • Simple Tool Interface Just HTML in, PDF out. No complex configuration
  • Secure & Flexible Storage Managed storage, BYOB, or fully stateless mode
agent-session.log

USER Create a summary report of our Q4 sales data

AGENT I'll analyze the Q4 data and generate a report.

> TOOL query_database(period="Q4")

> OK Retrieved 1,247 transactions

> TOOL generate_pdf(html="...")

> OK PDF generated successfully

AGENT Here's your Q4 Sales Report: [Download PDF]

Give Your AI Agents Superpowers

Connect your AI Agent via MCP in 30 seconds. 100 free credits coupon on signup.

Get Started Free Explore Use Cases