Stirling PDF Agent

CLI or API | MCP | Agent

Version: 2.3.0

Documentation — Installation, deployment, usage across the MCP, API, and CLI interfaces, and guidance for provisioning the Stirling PDF service are maintained in the official documentation.

📚 Table of Contents

• Overview
• Key Features
• Installation
• Quick Start & Usage Examples
• MCP Server Mode
  • Available MCP Tools
  • MCP Configuration Examples
• Agent Mode
  • Running the Agent CLI
  • Docker Compose Orchestration
• Environment Variables Reference
• Security & Governance
• Developer & Contribute Guidelines
• Documentation

Overview

Stirling PDF Agent is a production-grade Agent and Model Context Protocol (MCP) server designed to interface directly with Stirling PDF via REST APIs. It provides smooth capability to manipulate, edit, and overlay PDFs (e.g. adding watermarks) programmatically or using large language models.

Key Features

• Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts by grouping methods into optimized, togglable tool modules.
• Enterprise-Grade Security: Complete support for Eunomia policies, OIDC token delegation, and granular execution context tracking.
• Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
• Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.

Installation

Pick the extra that matches what the operator want to run:

# Connector-focused MCP server (includes the shared graph engine)
uv pip install "stirlingpdf-agent[mcp]"

# Agent runtime (adds model orchestration to the shared graph engine)
uv pip install "stirlingpdf-agent[agent]"

# Everything (development)
uv pip install "stirlingpdf-agent[all]"      # or: python -m pip install "stirlingpdf-agent[all]"

Container images (:mcp vs :agent)

One multi-stage docker/Dockerfile builds two right-sized images, selected by --target:

docker build --target mcp   -t knucklessg1/stirlingpdf-agent:mcp    docker/   # connector-focused MCP server
docker build --target agent -t knucklessg1/stirlingpdf-agent:2.3.0 docker/   # agent runtime

docker/mcp.compose.yml runs the connector-focused :mcp server; docker/agent.compose.yml runs the agent (:2.3.0) with a co-located :mcp sidecar. Both compose files require the deployed image to be pinned by digest via STIRLINGPDF_AGENT_MCP_IMAGE / STIRLINGPDF_AGENT_AGENT_IMAGE (e.g. knucklessg1/stirlingpdf-agent@sha256:<digest>) — least-privilege, read-only, non-root (10001:10001) containers with no floating tag in production.

Knowledge-graph database (epistemic-graph)

Both [mcp] and [agent] carry the epistemic-graph engine through the required Agent Utilities core dependency (epistemic-graph[full]). The [mcp] extra keeps the server connector-focused; [agent] also enables model orchestration. Local deployments can use the bundled engine. For production or shared state, run epistemic-graph as a dedicated database service and configure the runtime to use it. Deployment recipes (single-node + Raft HA), connection configuration, and architecture diagrams are documented in the epistemic-graph deployment guide.

Quick Start & Usage Examples

Using the underlying Stirling PDF Client wrapper directly in Python:

from stirlingpdf_agent.api_client import StirlingPdfApi

# Initialize the Stirling PDF client
client = StirlingPdfApi(
    base_url="http://localhost:8080",
    token="your-stirling-pdf-api-key",
)

# Example action: Add a watermark to an existing PDF
response = client.add_watermark(
    filepath="input.pdf",
    watermarkText="CONFIDENTIAL",
    percentOfPage=30,
    opacity=0.5,
    rotation=45,
)

# Save output PDF bytes
with open("watermarked_output.pdf", "wb") as f:
    f.write(response.data)

MCP Server Mode

This server use dynamic Action-Routed tools to optimize token overhead and maximize IDE compatibility.

Available MCP Tools

The table below is auto-generated from the MCP server — do not edit by hand.

Condensed action-routed tools (MCP_TOOL_MODE=condensed)

Verbose 1:1 API-mapped tools (MCP_TOOL_MODE=verbose or both)

2 action-routed tool(s) · 1 verbose 1:1 tool(s). Each is enabled unless its <DOMAIN>TOOL toggle is set false; MCP_TOOL_MODE selects the surface (intent default — the six verb-tools, granular set loaded on demand · condensed action-routed · verbose 1:1 · both). Auto-generated — do not edit.

Dynamic Tool Selection & Visibility

This MCP server supports dynamic toolset selection and visibility filtering at runtime. This allows the operator to restrict the set of exposed tools to prevent blowing up the LLM's context window.

The operator can configure tool filtering via multiple input channels:

• CLI Arguments: Pass --tools or --toolsets (or their disabled counterparts --disabled-tools and --disabled-toolsets) during startup.
• Environment Variables: Define standard environment variables:
  • MCP_ENABLED_TOOLS / MCP_DISABLED_TOOLS
  • MCP_ENABLED_TAGS / MCP_DISABLED_TAGS
• HTTP SSE Request Headers: Pass custom headers during transport initialization:
  • x-mcp-enabled-tools / x-mcp-disabled-tools
  • x-mcp-enabled-tags / x-mcp-disabled-tags
• HTTP SSE Request Query Parameters: Append query parameters directly to the operator's transport connection URL:
  • ?tools=tool1,tool2
  • ?tags=tag1

When query strings or parameters are provided, an LLM-free Knowledge Graph resolution layer (using DynamicToolOrchestrator) matches query intents against known tool tags, names, or descriptions, with safe fallback and automated 24-hour background cache refreshing.

MCP Configuration Examples

Install the connector-focused [mcp] extra. Examples use stirlingpdf-agent[mcp] to add FastMCP / FastAPI through agent-connector-sdk[mcp]; the required Agent Utilities core still carries epistemic-graph[full]. The [agent-runtime] extra additionally enables model orchestration.

stdio Transport (local IDEs — Cursor, Claude Desktop, VS Code)

{
  "mcpServers": {
    "stirlingpdf-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "stirlingpdf-agent[mcp]",
        "stirlingpdf-mcp"
      ],
      "env": {
        "MCP_TOOL_MODE": "intent",
        "PDFTOOL": "True"
      }
    }
  }
}

Runtime references require an alias-aware launcher such as Arbora. Other launchers must omit those entries and inject the resolved values through their own runtime secret boundary.

Streamable-HTTP Transport (networked / production)

{
  "mcpServers": {
    "stirlingpdf-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "stirlingpdf-agent[mcp]",
        "stirlingpdf-mcp",
        "--transport",
        "streamable-http",
        "--port",
        "8000"
      ],
      "env": {
        "TRANSPORT": "streamable-http",
        "HOST": "127.0.0.1",
        "PORT": "8000",
        "MCP_TOOL_MODE": "intent",
        "PDFTOOL": "True"
      }
    }
  }
}

Alternatively, connect to a pre-deployed Streamable-HTTP instance by url:

{
  "mcpServers": {
    "stirlingpdf-mcp": {
      "url": "http://localhost:8000/stirlingpdf-mcp/mcp"
    }
  }
}

Run a reviewed container image as a least-privilege stdio child (no listener or published port):

docker run -i --rm \
  --read-only \
  --cap-drop=ALL \
  --security-opt=no-new-privileges \
  --pids-limit=256 \
  --tmpfs /tmp:rw,noexec,nosuid,nodev,size=64m \
  -e TRANSPORT=stdio \
  -e MCP_TOOL_MODE=intent \
  -e PDFTOOL=True \
  registry.example.invalid/stirlingpdf-agent@sha256:<digest> stirlingpdf-mcp

For containerized network HTTP, supply an authenticated TLS ingress (or direct server TLS), exact MCP_ALLOWED_HOSTS, and an exact trusted-proxy CIDR policy through the operator-owned deployment profile. The generator does not emit an unauthenticated non-loopback listener.

Auto-generated from the code-read env surface (MCP_TOOL_MODE + package vars) — do not edit.

Additional Deployment Options

stirlingpdf-agent can run as a local stdio process or container, or behind a remote network boundary. The Deployment guide carries the detailed transport contract for all four transports — stdio, streamable-http, local container / uv, and remote URL:

• Local container / uv — launch the server from mcp_config.json via uvx, docker run, or podman run as a reviewed, least-privilege stdio child with no listener or published port, or point at a local streamable-http container by url.
• Remote URL — connect through an operator-supplied authenticated HTTPS ingress (for example a server deployed behind Caddy at https://stirlingpdf-mcp.example.invalid/mcp) using the "url" key. Keep its URL, outbound identity references, trust profile, and exact MCP_ALLOWED_HOSTS in AgentConfig.

Agent Mode

This repository features a fully integrated Pydantic AI Graph Agent. It communicates over the Agent Control Protocol (ACP) and interacts smoothly with the Agent Web UI (AG-UI) and Terminal interface.

Running the Agent CLI

To start the interactive command-line agent:

# Set credentials
export STIRLINGPDF_URL="<configured-endpoint>"
export STIRLINGPDF_API_KEY="your-api-key"

# Run the agent server
stirlingpdf-agent --provider openai --model-id gpt-4o

Docker Compose Orchestration

version: '3.8'

services:
  stirlingpdf-agent-mcp:
    image: example/stirlingpdf-agent@sha256:<digest>
    container_name: stirlingpdf-agent-mcp
    hostname: stirlingpdf-agent-mcp
    restart: always
    env_file:
      - .env
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=streamable-http
    ports:
      - "8000:8000"

  stirlingpdf-agent-agent:
    image: example/stirlingpdf-agent@sha256:<digest>
    container_name: stirlingpdf-agent-agent
    hostname: stirlingpdf-agent-agent
    restart: always
    depends_on:
      - stirlingpdf-agent-mcp
    env_file:
      - .env
    command: [ "stirlingpdf-agent" ]
    environment:
      - PYTHONUNBUFFERED=1
      - HOST=0.0.0.0
      - PORT=9004
      - MCP_URL=http://stirlingpdf-agent-mcp:8000/mcp
      - PROVIDER=${PROVIDER:-openai}
      - MODEL_ID=${MODEL_ID:-gpt-4o}
      - ENABLE_WEB_UI=True
      - ENABLE_OTEL=True
    ports:
      - "9004:9004"

Environment Variables

Package environment variables

Inherited agent-connector-sdk variables (apply to every connector)

17 package + 16 inherited variable(s). Auto-generated from .env.example + the shared agent-connector-sdk set — do not edit.

Reference

Stirling PDF Agent use both package-specific environment configurations and standard security settings inherited from the agent-connector-sdk system core.

Stirling PDF Agent Configs

• PDFTOOL (bool, default: True): Toggles the dynamic PDF action tool registration.
• STIRLINGPDF_URL (str, required): The base endpoint of the external Stirling PDF API service.
• STIRLINGPDF_API_KEY (str): API connection token/secret used to authenticate REST requests.
• TLS_PROFILE (str): Selects a named AgentConfig transport-security profile. Certificate and hostname verification are mandatory.
• TLS_PROFILES_REF (secret reference): Resolves the runtime-only TLS profile catalog.

Inherited agent-connector-sdk Configs

• TRANSPORT (str, default: stdio): Server transport type. Options: stdio, sse, streamable-http.
• HOST (str, default: 0.0.0.0): Network host interface to bind the HTTP server.
• PORT (int, default: 8000): Port to listen on.
• ENABLE_OTEL (bool, default: False): Enables OpenTelemetry tracing integration.
• ALLOWED_CLIENT_REDIRECT_URIS (str): Comma-separated list of approved redirect URLs for authentication loops.
• AUTH_TYPE (str): Server authentication mode configurations.
• EUNOMIA_TYPE (str, default: none): Policy configuration enforcement. Options: none, embedded, remote.
• EUNOMIA_POLICY_FILE (str): Path to local JSON configuration policy maps.
• EUNOMIA_REMOTE_URL (str): Target URL for remote auth policy coordination.
• OAUTH_BASE_URL (str): Base OAuth service endpoint.
• OAUTH_UPSTREAM_AUTH_ENDPOINT (str): Upstream OAuth service authorization endpoint.
• OAUTH_UPSTREAM_CLIENT_ID (str): Client application identity ID.
• OAUTH_UPSTREAM_CLIENT_SECRET (str): Client secret credential token.
• OAUTH_UPSTREAM_TOKEN_ENDPOINT (str): Remote OAuth token resolution endpoint.

Security & Governance

Built directly upon the enterprise-ready agent-connector-sdk core, standard security parameters are fully supported:

• Eunomia Policies: Fine-grained, policy-driven tool authorization. Supports none, local embedded (mcp_policies.json), or centralized remote modes.
• OIDC Token Delegation: Compliant with RFC 8693 token exchange for flowing authenticating user credentials from Web UI / ACP → Agent → MCP.
• Scoped Credentials: Execution context runs restricted to the specific caller identity.

Contribute

Contributions are welcome! Please ensure code quality by running local checks before submitting pull requests:

• Format code using ruff format .
• Lint code using ruff check .
• Validate type-safety with mypy .
• Ran test suites using pytest

Documentation

The complete documentation is published as the official documentation site and is the recommended reference for installation, deployment, and day-to-day operation.

AGENTS.md is the canonical contributor/agent guidance.

Deploy with agent-os-genesis

This package can be provisioned for you — skill-guided — by the agent-os-genesis universal skill (its single-package deploy mode): it picks your install method, seeds secrets to OpenBao/Vault (or .env), trusts your enterprise CA, registers the MCP server, and verifies it — the same machinery that stands up the whole Agent OS, narrowed to just this package. Ask your agent to "deploy stirlingpdf-agent with agent-os-genesis".

Secrets are read-existing + seeded via vault_sync — you are only prompted for what's missing.

Deploy with agent-connector-sdk-deployment

Provision this package with the consolidated agent-connector-sdk-deployment workflow. It selects an installed-package, editable-source, or immutable-container path; records only runtime secret and TLS-profile references in AgentConfig; and runs doctor, registration, policy, observability, and rollback gates. Ask your agent to "deploy stirlingpdf-agent with agent-connector-sdk-deployment".

The repository embeds no deployment profile, credential value, certificate path, or environment-specific endpoint. Supply those at runtime through AgentConfig and the configured secret provider.

Governed capability contract

This package ships a compact canonical skill surface with specialist procedures kept as referenced workflows. The current MCP tools, skill metadata, connector_manifest.yml, ontology, mappings, shapes, fixtures, migrations, tool-schema fingerprints, and certification metadata form one versioned capability contract. Validate them together; do not rely on stale tool names or historical per-task skill wrappers.

Runtime endpoints, credentials, certificate trust, tenant identity, retention, and observability policy are deployment inputs and are never packaged values. See Configuration, trust, and privacy before enabling a network transport, connector ingestion, Arbora delegation, or trace export.