How to Use the iLovePDF MCP in AutoGen

Q: Can one AutoGen agent upload a file and another process it using iLovePDF?

Yes. One agent can call uploadpdfbyurl and pass the resulting task ID to another agent to run processpdftask.

Let your AutoGen agents debate and execute complex document workflows using this iLovePDF MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iLovePDF MCP to AutoGen

Create your Vinkius account to connect iLovePDF to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup iLovePDF with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent document coordination with MCP

`start_pdf_task` initiates the document processing pipeline based on instructions from your coordinator agent. A separate critic agent can verify the parameters before execution. This collaborative approach ensures that tasks like compression or splitting are only run when necessary. The agents negotiate the best approach before calling the API.

Asynchronous task monitoring

`get_task_status` allows your execution agent to poll the server for progress updates. Meanwhile, other agents can continue preparing subsequent steps or drafting reports. This keeps your conversation loop active without blocking. The agents naturally resume the document pipeline once the status returns as completed.

Secure file handoff

`get_pdf_download_link` retrieves the final file location once the processing is done. Your communication agent then delivers this link directly to the user. If any step fails, `list_pdf_tasks` helps the agents diagnose what went wrong. They can look at recent tasks, adjust parameters, and try again.

Setup guide

Set up iLovePDF MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes iLovePDF tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="iLovePDF_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent iLovePDF data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="iLovePDF_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent iLovePDF data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by iLovePDF. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect iLovePDF now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about iLovePDF MCP in AutoGen

You register the server tools with your AssistantAgent. The agents then decide when to call tools like `start_pdf_task` during their conversation.

Yes. One agent can call `upload_pdf_by_url` and pass the resulting task ID to another agent to run `process_pdf_task`.

The agents discuss the error returned by the tool. They can automatically adjust the task parameters and re-run the process.

Yes. You can filter the tools list before passing them to the agent constructor, restricting access to specific tools like compression.

Your PDF documents run within temporary, secure memory spaces. The server deletes files immediately after processing is finished, preventing unauthorized access or persistent storage.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript