How to Use the PDF.co MCP in AutoGen

Q: How do AutoGen agents resolve conflicts during a PDF.co conversion?

One agent might run pdftojson while another runs pdftotext. They compare the output density and debate which format is better suited for the current task before proceeding.

Q: Can AutoGen agents track long-running PDF.co jobs?

Yes, a dedicated monitor agent polls the checkjobstatus tool. It reports back to the coordinator agent when the async job completes, keeping the conversation active without blocking other agents.

Q: How do I configure the PDF.co MCP Server for AutoGen?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP endpoint. Pass the resulting tool list to your AssistantAgent constructor and use the MCP adapter to handle schema conversions.

Let your AutoGen agents debate and coordinate document conversions using PDF.co tools for consensus-driven workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PDF.co MCP to AutoGen

Create your Vinkius account to connect PDF.co to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup PDF.co with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Collaborative document processing in AutoGen

The `pdf_to_json` tool provides the raw structural data that your AutoGen analyst agent needs to inspect a document. While the analyst agent extracts the tables, a separate validation agent reviews the output JSON to check for parsing errors. If the validation agent flags an error, it requests the coordinator agent to run `ocr_image` instead. The agents debate the accuracy of both results before saving the final verified text to your database.

Automated security consensus with PDF.co MCP Server

The `protect_pdf` tool is triggered when your AutoGen security agent identifies sensitive information in a generated report. The security agent refuses to approve the workflow until a password is set, debating with the performance agent about compliance rules. Once the agents agree on the security parameters, the writer agent uses `merge_pdfs` to combine the files, and the security agent applies the password. This multi-agent negotiation runs entirely through our MCP connection to ensure that no unencrypted documents leave the system.

Multi-agent file splitting and processing pipelines

The `split_pdf` tool lets your coordinator agent break a large document into individual pages for parallel analysis. The coordinator distributes these pages to multiple worker agents, who process their assigned pages simultaneously. Each worker agent uses `pdf_to_text` to extract the content of its page. Once all workers finish, they submit their findings to a summarizer agent, who compiles the final report and checks the balance using `get_account_info`.

Setup guide

Set up PDF.co 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 PDF.co 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="PDF.co_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent PDF.co 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="PDF.co_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent PDF.co 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 PDF.co. 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 PDF.co 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 PDF.co MCP in AutoGen

One agent might run `pdf_to_json` while another runs `pdf_to_text`. They compare the output density and debate which format is better suited for the current task before proceeding.

Yes, a dedicated monitor agent polls the `check_job_status` tool. It reports back to the coordinator agent when the async job completes, keeping the conversation active without blocking other agents.

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP endpoint. Pass the resulting tool list to your `AssistantAgent` constructor and use the MCP adapter to handle schema conversions.

Yes, if the security agent detects an encrypted file, it just instructs the executor agent to run `unprotect_pdf` with the provided password, making the text accessible to the rest of the agent conversation.

All CSV, XML, and PDF data sent to the API is protected by end-to-end transport encryption and wiped from servers within hours of completion. The Vinkius sandbox isolates the execution context, meaning your document payloads are never cached or stored long-term.

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