How to Use the DocBreach MCP in AutoGen

Q: How do AutoGen agents coordinate using DocBreach?

One planning agent can call docs.map to understand the site structure, then assign specific page URLs to execution agents. Those agents then use docs.read to fetch clean Markdown and complete their assigned code-generation tasks.

Let your AutoGen agents debate and extract clean API specifications without fighting web scrapers.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DocBreach MCP to AutoGen

Create your Vinkius account to connect DocBreach 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 DocBreach with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve API spec debates using direct documentation lookups

`docs.read` provides raw, clean Markdown directly to your AutoGen conversation thread. When your coding agent and testing agent disagree on an API payload structure, they invoke this tool to fetch the ground truth. This direct access eliminates guesswork during multi-agent discussions. The agents parse the clean Markdown response, resolve their conflict, and proceed with code generation based on verified documentation.

Map entire developer sites for AutoGen multi-agent planning

`docs.map` retrieves the complete structure of a documentation site so your planning agent can coordinate tasks. Before any code is written, the planning agent uses this map to divide reading tasks among other agents. This organized approach keeps your AutoGen workspace clean. Instead of multiple agents searching the web randomly, they target specific paths extracted by this DocBreach MCP Server tool.

Extract structured OpenAPI endpoints for AutoGen agents

`docs.extract` parses OpenAPI, Swagger, or Postman specs directly inside the Vinkius sandbox. Your integration agent calls this tool to isolate specific endpoints, passing only the necessary schemas to the code-generation agent. This targeted extraction prevents context window overflow in long multi-agent conversations. This MCP tool strips out the noise so your agents can focus strictly on the JSON schemas and parameters they need to implement.

Setup guide

Set up DocBreach 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 DocBreach 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="DocBreach_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One planning agent can call `docs.map` to understand the site structure, then assign specific page URLs to execution agents. Those agents then use `docs.read` to fetch clean Markdown and complete their assigned code-generation tasks.

Yes, any agent in your AutoGen group can invoke the tools. The schema conversion is handled automatically by the adapter, making tools like `docs.extract` available to all agents in the conversation.

Initialize the client using the HTTP transport, then fetch the tool list using the adapter. Pass this list directly to the AssistantAgent constructor so your conversational agents can call them during debates.

No, the server parses target documentation pages, PDFs, and API schemas directly without running a heavy browser engine. This headless approach keeps execution fast and lightweight within the sandbox.

All API specs and target URLs processed by the server are isolated within your private Vinkius sandbox. The runtime is ephemeral, meaning no documentation data persists after your AutoGen execution session ends.

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