MCP Integration
The Model Context Protocol (MCP) enables AI coding assistants to interact directly with docpenny’s PDF generation engine. Once configured, your assistant can list templates, submit jobs, check job status and credits, and generate previews from your editor or terminal.
Prerequisites
- A docpenny account with an active API key
- An AI coding harness that supports the Streamable HTTP MCP transport
Creating an API Key
- Go to Settings → API Keys in the docpenny dashboard
- Click Create New Key, give it a descriptive name (e.g., “MCP Assistant”)
- Copy the key immediately — it will not be shown again
MCP Endpoint
The MCP server is available at:
- Production:
https://mcp.docpenny.com/mcp
Every request requires the x-api-key header:
x-api-key: <your_api_key>Available Tools
Once connected, your assistant has access to six tools:
| Tool | Description |
|---|---|
list_templates | List available PDF templates with optional pagination. Use source="system" to see pre-built system templates. |
get_template | Get detailed information about a specific template, including its variables and JSON schema. |
submit_job | Submit a new PDF generation job using a template and a JSONL string. Each line in the data string produces one PDF. |
get_job | Get the status and progress of a PDF generation job, including task counts. |
get_credits | Check the organization’s credit balance, including paid and free credits. |
generate_preview | Generate a watermarked preview PDF (no credits consumed) for one-time download. |
Harness Configuration
Select your AI coding assistant for step-by-step setup: