How to Use the GUIDEcx MCP in AutoGen

Q: How do I register GUIDEcx tools with an AutoGen agent?

Use mcpservertools with your Vinkius server URL to fetch the tool definitions. Pass this list directly to your AssistantAgent constructor to give it access to tasks and projects.

Q: Can multiple AutoGen agents coordinate on a single GUIDEcx project?

Yes, one agent can call getproject to analyze the scope while another calls listprojectusers to assign tasks. They share this context in their group chat to make collaborative decisions.

Deploy AutoGen agents that debate project health, coordinate tasks, and log time directly in your GUIDEcx workspace.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect GUIDEcx MCP to AutoGen

Create your Vinkius account to connect GUIDEcx 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 GUIDEcx with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-driven project setup in AutoGen

The `create_project` tool executes only after your AutoGen PM agent and QA agent agree on the onboarding parameters. This multi-agent debate ensures that projects are never created with missing fields or incorrect client configurations. By forcing agents to negotiate the details before hitting the API, you eliminate manual cleanup. The resulting project matches your exact operational standards right from the start.

Multi-agent task triaging via GUIDEcx MCP Server

Your coordinator agent calls `list_tasks` to identify overdue milestones, then presents them to specialized worker agents. Once the designated agent resolves the blocker, it calls `update_task` to log the progress and notify the team. This collaborative loop prevents tasks from slipping through the cracks. The agents verify each other's work before marking any onboarding milestone as complete.

Collaborative time tracking audits

You use `list_time_records` to let a financial agent inspect logged hours while an operations agent reviews task completion. They compare notes to verify that the logged effort matches the actual work delivered. If they find a discrepancy, the financial agent triggers `create_time_record` to adjust the logs. This automated audit trail keeps your client billing accurate without manual oversight.

Setup guide

Set up GUIDEcx 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 GUIDEcx 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="GUIDEcx_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use `mcp_server_tools` with your Vinkius server URL to fetch the tool definitions. Pass this list directly to your `AssistantAgent` constructor to give it access to tasks and projects.

Yes, one agent can call `get_project` to analyze the scope while another calls `list_project_users` to assign tasks. They share this context in their group chat to make collaborative decisions.

You can set up a coordinator agent that reviews task states before calling `update_task`. This prevents agents from overwriting each other's progress updates during execution.

Yes, you can connect using either standard stdio or streamable HTTP. This MCP Server gives your multi-agent system flexible connection options depending on your hosting environment.

Yes, all user profiles, email addresses, and assignment lists retrieved via `list_users` are encrypted in transit. Vinkius runs the integration in a secure MCP sandbox, preventing any third-party leaks of your internal staff data.

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