How to Use the R2R MCP in AutoGen

Q: How do AutoGen agents resolve conflicts using R2R data?

One agent runs search to gather facts. If another agent disagrees, it can call getdocument to inspect the source file directly and resolve the debate.

Q: Can I restrict AutoGen agents to specific R2R document collections?

Yes, you can configure your coordinator agent to call listcollections first. It then instructs the worker agents to only query specific collection IDs.

Q: What happens if the database goes down during a conversation?

Your monitor agent can call gethealth to detect the outage. It can then pause the conversation or alert the user instead of letting the agents hallucinate answers.

Let your AutoGen agents debate and verify facts using direct access to your R2R document collections.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect R2R MCP to AutoGen

Create your Vinkius account to connect R2R 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 R2R with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven document analysis

Give your agents the tools to double-check each other. One AutoGen agent can run a `search` to pull raw document chunks, while a critic agent uses `get_document` to verify the source metadata and challenge the findings. This collaborative loop reduces errors. By forcing agents to negotiate using real data, you get highly accurate answers that are backed by actual files rather than creative guessing.

Multi-agent RAG queries with AutoGen

Let your agents run complex retrieval loops. An agent can execute `rag_query` to get a synthesized summary of a topic over the MCP connection, then share that summary with other agents in the conversation group to drive decision making. You can organize these operations by project. Agents can call `list_collections` to identify the right data groups and keep their discussions focused on the correct set of files.

Health monitoring and document inventory

Keep your multi-agent conversations running smoothly. A coordinator agent can check `get_health` to make sure the document store is online before delegating tasks to the rest of the group. When new tasks arrive, the coordinator can run `list_documents` using this MCP server to see what files are currently ingested. This allows the system to assign retrieval jobs based on what data is actually available.

Setup guide

Set up R2R 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 R2R 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="R2R_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent R2R 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="R2R_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent R2R 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 R2R. 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 R2R 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 R2R MCP in AutoGen

One agent runs `search` to gather facts. If another agent disagrees, it can call `get_document` to inspect the source file directly and resolve the debate.

Yes, you can configure your coordinator agent to call `list_collections` first. It then instructs the worker agents to only query specific collection IDs.

You use the MCP tool adapter to convert the schemas. Pass the resulting tool list to your AssistantAgent instances so they can call `rag_query` during debates.

Your monitor agent can call `get_health` to detect the outage. It can then pause the conversation or alert the user instead of letting the agents hallucinate answers.

All document content and search operations run inside an MCP sandbox. This keeps your raw text isolated from other agents and prevents cross-tenant data leaks.

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