Skip to content

stirlingpdf-agent

Stirling PDF MCP Server + A2A Agent for the Arbora ecosystem — a typed, deterministic toolkit for performing PDF operations through a Stirling PDF service.

Official documentation

This site is the canonical reference for stirlingpdf-agent, maintained alongside every release.

PyPI MCP Server License GitHub

Overview

stirlingpdf-agent wraps the Stirling PDF REST API with typed MCP tools and an optional Pydantic-AI agent server. It provides:

  • StirlingPdfApi — a requests-based REST client over the Stirling PDF /api/v1 surface, configured from the environment via get_client().
  • An action-routed MCP tool — a single pdf_action dispatcher that invokes any supported operation (for example, add_watermark) on the connected Stirling PDF service.
  • An A2A agent server — a Pydantic-AI agent (console script stirlingpdf-agent) that drives the MCP tools for multi-step workflows.

The connector remains inactive when credentials are absent, degrading safely until a Stirling PDF service is configured.

Explore the documentation

  • :material-rocket-start: Installation — pip, source, extras, and the prebuilt Docker image.
  • Deployment — run the MCP and agent servers, Docker Compose, Caddy + Technitium.
  • Usage — the MCP tool surface, the StirlingPdfApi client, and the CLI.
  • Backing Platform — deploy Stirling PDF with Docker.
  • Architecture — the agent-package pattern and tool routing.
  • Concepts — the CONCEPT:STIRLINGPDF-* registry.

Quick start

pip install stirlingpdf-agent
stirlingpdf-mcp                       # stdio MCP server (default transport)

Connect it to a Stirling PDF service:

export STIRLINGPDF_URL=<configured-endpoint>
export STIRLINGPDF_API_KEY=your_token
stirlingpdf-mcp --transport streamable-http --host 0.0.0.0 --port 8000

See Installation and Deployment for the full matrix (PyPI extras, Docker image, all transports, the agent server, reverse proxy, DNS).

Spec delivery

The spec delivery dashboard reports the generated delivery status for this connector.