How to Use the GroundX MCP in AutoGen

Q: How do AutoGen agents coordinate when calling GroundX ingestion tools?

One AutoGen agent can call ingestdocuments while another agent loops on getingeststatus. They communicate via text messages to hand off control once the processing is complete.

Q: Can I restrict which AutoGen agents have access to GroundX search tools?

Yes, you can pass the tool list containing searchcontent only to specific agents in your AutoGen group chat. This prevents non-research agents from making unnecessary tool calls.

Q: How do I set up GroundX tools in AutoGen using the MCP adapter?

Install autogen-extmcp and use mcpservertools with your Vinkius server URL. Pass the generated tools array directly to your AutoGen AssistantAgent constructor.

Q: How do AutoGen agents handle errors from ingestwebsite?

If ingestwebsite fails, your AutoGen critic agent can analyze the error message and instruct the researcher agent to try a different URL or fallback to local document upload.

Run multi-agent debates over your GroundX search results using AutoGen and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GroundX MCP to AutoGen

Create your Vinkius account to connect GroundX 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 GroundX with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve GroundX search conflicts in AutoGen

The `search_content` tool allows your AutoGen researcher agent to pull semantic matches from your document buckets. Once retrieved, a separate critic agent challenges the search results to ensure they actually answer the user's prompt. This consensus-driven loop guarantees that your AutoGen agents only use verified facts. If the critic agent finds gaps, it instructs the researcher agent to run `search_documents` with different metadata filters.

Automate document ingestion with AutoGen agents

The `ingest_documents` tool lets an AutoGen coordinator agent upload local files or URLs directly to a specific bucket. The coordinator agent then tasks a monitoring agent with calling `get_ingest_status` until the files are parsed. This division of labor keeps your AutoGen ingestion pipelines reliable and hands-free. After the monitoring agent confirms the status is complete, a final writer agent uses `list_content` to verify the files are ready.

Let AutoGen agents manage this MCP Server

The `create_group` tool enables your AutoGen manager agent to organize multiple buckets into logical sets for different agent teams. For example, a finance agent team can have its own group, separate from the engineering team's group. This dynamic organization prevents agent confusion and limits token waste during multi-agent conversations run over MCP. The manager agent uses `list_groups` to audit access and ensure that search tools only query relevant data.

Setup guide

Set up GroundX 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 GroundX 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="GroundX_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One AutoGen agent can call `ingest_documents` while another agent loops on `get_ingest_status`. They communicate via text messages to hand off control once the processing is complete.

Yes, you can pass the tool list containing `search_content` only to specific agents in your AutoGen group chat. This prevents non-research agents from making unnecessary tool calls.

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius server URL. Pass the generated tools array directly to your AutoGen `AssistantAgent` constructor.

If `ingest_website` fails, your AutoGen critic agent can analyze the error message and instruct the researcher agent to try a different URL or fallback to local document upload.

Every search query and document chunk processed by the platform is isolated within a secure V8 sandbox using the Vinkius MCP gateway. This zero-trust architecture ensures your proprietary business data and agent conversations remain completely private.

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