How to Use the Docamatic MCP in AutoGen

Q: How do AutoGen agents coordinate when using Docamatic?

One agent can handle data collection, another triggers generatepdffromtemplate, and a third verifies the output history using listgenerationhistory to confirm successful generation.

Q: Can I use Docamatic to let AutoGen agents review visual layouts?

Yes. Agents can use generateimagefromhtml to render a layout, then pass the image to a vision-enabled agent to check for alignment issues.

Let your AutoGen agents debate, generate, and verify pixel-perfect PDF invoices and reports through collaborative workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Docamatic MCP to AutoGen

Create your Vinkius account to connect Docamatic 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 Docamatic with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative document generation and verification

In an AutoGen setup, a writer agent can draft the content while a formatting agent uses `generate_pdf_from_html` to render the document. A third critic agent can then inspect the output to ensure it matches your brand guidelines before final approval. If the layout is off, the critic agent requests adjustments, and the formatting agent calls `add_elements_to_pdf` to fix coordinates or text placement. This automated feedback loop ensures high-quality PDF outputs without human review.

Multi-agent consensus on template selection

When generating client facing materials, your AutoGen agents can debate which layout to use. One agent queries `list_available_builtin_templates`, while another checks client preferences to select the optimal design for `generate_pdf_from_template`. Once they agree on the layout, they compile the JSON data and trigger the document generation. This consensus-driven approach prevents formatting mistakes and ensures the output matches the recipient's system requirements.

Automate screenshot verification with this MCP Server

To verify that a web app renders correctly, one agent can trigger `take_web_screenshot` while another analyzes the image for visual bugs. If problems are found, they coordinate to document the errors in a generated PDF report. They can also compile multiple visual tests into a single file using `merge_multiple_pdfs`, creating a clean audit trail that your team can review later.

Setup guide

Set up Docamatic 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 Docamatic 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="Docamatic_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent can handle data collection, another triggers `generate_pdf_from_template`, and a third verifies the output history using `list_generation_history` to confirm successful generation.

Yes. Agents can use `generate_image_from_html` to render a layout, then pass the image to a vision-enabled agent to check for alignment issues.

The agents debate the correct order of documents, then pass the finalized, ordered list of file paths to `merge_multiple_pdfs` to execute the merge.

Yes. The MCP Server tools are registered as functions that any agent in your group chat can call when the conversation flow requires document generation.

All rendering operations occur inside isolated, temporary environments. Your source HTML, images, and PDF inputs are deleted instantly after processing, leaving no trace on the server.

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