Compatible with every major AI agent and IDE
What is the Stirling PDF MCP Server?
Connect your Stirling PDF instance to any AI agent and take full control of your document workflows through natural conversation. This server allows you to process PDF files, convert formats, and monitor your self-hosted infrastructure.
What you can do
- Document Manipulation — Add text watermarks with custom opacity and font sizes, or convert images directly into PDF documents.
- Digital Security — Sign PDF documents using certificates with specific reasons and location metadata.
- Server Monitoring — Track application status, version info, and detailed request metrics (POST/GET) across all endpoints.
- Advanced Operations — Use the generic tool runner to access specialized features like merging, splitting, or extracting images from PDFs.
- Enterprise Metrics — Access Prometheus metrics for deep observability into your document processing pipeline.
How it works
- Subscribe to this server
- Enter your Stirling PDF Base URL and API Key
- Start processing documents from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Developers — Automate PDF processing tasks directly from your IDE or terminal.
- System Administrators — Monitor the health and load of your Stirling PDF instance in real-time.
- Legal & Admin Teams — Quickly sign or watermark documents without leaving your AI chat interface.
Built-in capabilities (11)
Add a watermark to a PDF document
Sign a PDF document with a certificate
Get POST requests count for all endpoints
Get unique users count for all endpoints
Get total count of GET requests
Get Prometheus metrics (requires Enterprise tier)
Get total count of POST requests
Get application status and version information
Get count of unique users for POST requests
Convert an image to a PDF document
Pass additional parameters as a JSON string. Run any Stirling PDF tool by its ID
Why OpenAI Agents SDK?
The OpenAI Agents SDK auto-discovers all 11 tools from Stirling PDF through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Stirling PDF, another analyzes results, and a third generates reports, all orchestrated through Vinkius.
- —
Native MCP integration via
MCPServerSse, pass the URL and the SDK auto-discovers all tools with full type safety - —
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
- —
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
- —
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
Stirling PDF in OpenAI Agents SDK
Stirling PDF and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Stirling PDF to OpenAI Agents SDK through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Stirling PDF in OpenAI Agents SDK
The Stirling PDF MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 11 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in OpenAI Agents SDK only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Stirling PDF for OpenAI Agents SDK
Every tool call from OpenAI Agents SDK to the Stirling PDF MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I add a text watermark to a PDF document using this server?
Yes! Use the add_watermark tool. You can specify the text, font size, and opacity to apply a professional watermark to any PDF file provided in base64 format.
How do I monitor the traffic and load on my Stirling PDF instance?
You can use get_requests to see POST counts, get_load for GET requests, or get_prometheus_metrics if you are on the Enterprise tier for detailed observability.
Is it possible to perform other operations like merging or splitting PDFs?
Yes, the run_generic_tool action allows you to execute any Stirling PDF tool by its ID (e.g., 'merge-pdfs' or 'split-pages') by passing the required parameters.
How does the OpenAI Agents SDK connect to MCP?
Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.
Can I use multiple MCP servers in one agent?
Yes. Pass a list of MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.
Does the SDK support streaming responses?
Yes. The SDK supports SSE and Streamable HTTP transports, both of which work natively with Vinkius.
MCPServerStreamableHttp not found
Ensure you have the latest version: pip install --upgrade openai-agents
Agent not calling tools
Make sure your prompt explicitly references the task the tools can help with.
Explore More MCP Servers
View all →
Razorpay
12 toolsAutomate online payments via Razorpay — manage orders, payments, and refunds directly from any AI agent.

Ebby
10 toolsEquip your AI agent to manage audio transcriptions, track processing status, and retrieve text via the Ebby API.

DataScope
6 toolsCreate mobile forms for field inspections, audits, and data collection that work offline and sync when connectivity returns.

Vagaro
10 toolsManage appointments, clients, staff, services, and retail for your Vagaro-powered salon, spa, or fitness business through natural conversation.
