How to Use the DevDocs MCP in AutoGen

Q: How do I pass DevDocs MCP Server tools to an AutoGen agent?

Use mcpservertools with your transport parameters. Pass that generated list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents use the DevDocs tools simultaneously?

Yes. Any agent configured with the tool adapter can call searchdocs or readpage during their turn in the conversation.

Q: How does the agent know which framework version to check?

The agent executes listlibraries first. It reads the available slugs, like aws or vue3, and targets the specific version relevant to the debate.

Q: Does AutoGen format the DevDocs Markdown automatically?

The McpToolAdapter handles the JSON-RPC schema conversion. The agent receives the raw Markdown text exactly as the API provides it.

Equip your AutoGen agents with DevDocs access. Let them debate API implementations using real, up-to-date documentation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DevDocs MCP to AutoGen

Create your Vinkius account to connect DevDocs 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 DevDocs with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve coding arguments with DevDocs

This MCP Server feeds factual API documentation into your AutoGen multi-agent conversations. When a coder agent suggests a deprecated method, the reviewer agent fires off `search_docs` to check the actual manual. They stop guessing and start reading. The consensus-driven architecture means one agent can run `list_libraries` to verify framework support, while another parses the results to form a counterargument.

Feed clean text to AutoGen agents

The `read_page` tool returns cleanly formatted Markdown text straight into the conversation thread. This prevents the context window from bloating with useless HTML navigation elements. Your agents read the exact same API specs a human would. `McpToolAdapter` handles the schema conversion automatically, so the raw documentation drops right into the debate without manual formatting.

Connect the DevDocs MCP Server

Setting up these specific documentation tools requires passing your HTTP transport endpoint to `mcp_server_tools`. The AssistantAgent constructor takes the resulting list and immediately understands how to query the DevDocs index. You dictate the transport layer. Whether you use stdio or Streamable HTTP, the agents gain instant access to find the exact manual page path they need to win an argument.

Setup guide

Set up DevDocs 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 DevDocs 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="DevDocs_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` with your transport parameters. Pass that generated list directly into your `AssistantAgent` constructor.

Yes. Any agent configured with the tool adapter can call `search_docs` or `read_page` during their turn in the conversation.

The agent executes `list_libraries` first. It reads the available slugs, like aws or vue~3, and targets the specific version relevant to the debate.

The `McpToolAdapter` handles the JSON-RPC schema conversion. The agent receives the raw Markdown text exactly as the API provides it.

The integration strictly handles public API documentation queries and framework slugs. Your internal AutoGen debate transcripts remain local and are never sent to the documentation host.

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