Connect Any AI Agent to PDF Generation with MCP

Most AI agent integrations follow the same pattern: you wrap an API in a function, describe it to the model, and hope the JSON it returns matches your schema. It works, but it’s fragile — schema drift, inconsistent field names, and missing error context all become your problem.

The Model Context Protocol (MCP) takes a different approach. It’s a standard that lets language models discover and call tools natively, with rich type information and structured error feedback built in. pdfs.build exposes its entire rendering pipeline as an MCP server — which means any MCP-compatible agent can generate documents without you writing a single line of integration code.

How it works

When your agent connects to the pdfs.build MCP server, it gains access to a set of tools:

list_templates — browse available templates with their schemas
render_template — render a template with a data payload, returns a PDF URL
get_schema — fetch the exact schema for a given template

The agent can call these tools mid-conversation. If a user says “send me an invoice for last month’s consulting work,” the agent can look up the invoice template, map the conversation context to the schema fields, and render a PDF — all in one turn.

Setting up the MCP connection

In your agent configuration, add the pdfs.build MCP server endpoint:

{
  "mcpServers": {
    "pdfreport": {
      "url": "https://backend.pdfs.build/mcp",
      "headers": {
        "Authorization": "Bearer prs_your_key_here"
      }
    }
  }
}

That’s the entire setup. The agent will automatically discover the available tools and their input schemas on first connection.

Example: Claude generating an invoice

Here’s what a Claude conversation with MCP looks like from the agent’s perspective:

User: “Can you generate an invoice for the October project?”
Claude calls list_templates → finds invoice-v3
Claude calls get_schema for invoice-v3 → learns the required fields
Claude maps conversation context to the schema, filling in client name, line items, and dates
Claude calls render_template with the data → receives a PDF URL
Claude responds: “Here’s your invoice: [download link]”

The model handles the data mapping. You handle the template design. No glue code in between.

Why this matters for document-heavy workflows

Traditional document generation requires a developer to write mapping logic for every template change. With MCP, the model reads the schema directly and adapts. Update your invoice template to add a new “project code” field, and any connected agent immediately knows it’s available — no deployment required.

This is particularly valuable for:

Finance and ops teams where documents change frequently
Customer-facing agents that generate personalized reports on demand
Internal tools where non-engineers need to trigger document generation

Getting your MCP key

MCP connections use the same API keys as the REST API. Create one at Settings → API Keys in your dashboard. The key prefix (prs_) is the same — the MCP server and REST API share the same authentication layer.

Check the API Reference for the full list of MCP-exposed tools and their schemas.

Back to blog