How to Use the Holded MCP in AutoGen

Q: Can AutoGen agents update product stock levels in Holded?

Yes, any agent in your group chat can invoke updateproductstock if the group decides an update is necessary. They just need to agree on the warehouse ID and quantity first.

Let your AutoGen agents debate billing discrepancies and manage Holded inventory through collaborative decision-making.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Holded MCP to AutoGen

Create your Vinkius account to connect Holded 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 Holded with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let AutoGen agents debate billing and project status

Build a multi-agent system where one agent pulls invoice data using `list_invoices` while another checks project tasks with `list_all_tasks`. They can debate whether a client has been billed correctly based on the actual work done. This consensus-driven approach prevents billing errors before they reach your clients. The agents resolve discrepancies internally, only alerting you when they find a mismatch that requires human intervention.

Run automated stock audits with this MCP Server

Set up a dedicated inventory agent that monitors your catalog using `list_products`. If stock for a high-demand item drops, it negotiates with a purchasing agent to determine the correct reorder quantity before running `update_product_stock`. By separating the analysis from the execution, you reduce the risk of ordering errors. The agents double-check the warehouse configuration using `get_product_details` before making any live writes to your database.

Coordinate client onboarding across multiple agents

Coordinate your client onboarding by letting agents collaborate on contact creation and project mapping. This MCP Server lets you pull client profiles via `list_contacts` while another agent checks active timelines using `list_projects`. They coordinate to ensure new clients are assigned to projects with available capacity. The entire process runs autonomously, using `get_contact_details` to verify billing data before any work begins.

Setup guide

Set up Holded 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 Holded 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="Holded_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You register the tools with your AssistantAgent using the MCP adapter. This gives your agents direct access to endpoints like `list_invoices` and `get_api_profile` during their conversations.

Yes, any agent in your group chat can invoke `update_product_stock` if the group decides an update is necessary. They just need to agree on the warehouse ID and quantity first.

You can set up a moderator agent to review all proposed writes, such as stock updates. The moderator inspects the tool inputs before letting the execution agent commit the changes to your account.

Yes, you can run multiple instances of the server on Vinkius, each with its own API key. You then assign different agents to manage different accounts or warehouses depending on your organizational setup.

Your financial transactions, task lists, and client contacts are protected by Vinkius's zero-trust architecture. All tool executions occur inside isolated, short-lived sandboxes, ensuring your business operations remain completely secure.

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