How to Use the BoldDesk MCP in AutoGen

Q: How do I install the BoldDesk toolset in my AutoGen project?

Run pip install -U "autogen-extmcp" to get the required extension. After that, initialize the BoldDesk MCP Server via mcpservertools and pass the resulting tools to your assistant agents.

Q: What happens if an agent tries to assign a ticket to an offline BoldDesk agent?

Your AutoGen agents should first run listagents or getagent to check availability. If the target agent is offline, the planning agents can debate alternative assignments before calling updateticket.

Let your AutoGen agents debate ticket resolution and update BoldDesk support queues directly without human intervention.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BoldDesk MCP to AutoGen

Create your Vinkius account to connect BoldDesk 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 BoldDesk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate ticket escalation with AutoGen agents

Your AutoGen agents can debate customer priority levels using `get_ticket` and `list_tickets` before committing to a support tier. One agent analyzes sentiment from the customer's previous history, while another evaluates team capacity to decide who gets the assignment. Once the agents reach a consensus, the winning agent executes `update_ticket` to assign the case. This setup stops premature escalations by forcing your agents to agree on the ticket's true urgency first.

Verify contacts via the BoldDesk MCP Server

When a high-priority message arrives, the BoldDesk MCP Server lets your AutoGen agents fetch customer profiles with `get_contact` and `list_contacts` to verify their service level agreements. This prevents agents from making assumptions about customer status during their planning phase. A dedicated billing agent can cross-reference the contact details with internal databases, while a support agent uses `add_ticket_note` to log the verified status on the ticket. They debate the customer's contract terms in your runtime, then update the ticket thread only after confirming the details.

Draft and debate public replies before sending

Your AutoGen team drafts public responses using `reply_to_ticket` and logs internal context using `add_ticket_note` only after rigorous peer review. A quality assurance agent checks the draft for tone, while a technical agent verifies the troubleshooting steps before any message goes live. If the QA agent flags the draft as too technical, it rejects the response and forces a rewrite. The agents update the ticket status via `update_ticket` only when both agree that the response is ready for the customer.

Setup guide

Set up BoldDesk 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 BoldDesk 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="BoldDesk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Run `pip install -U "autogen-ext[mcp]"` to get the required extension. After that, initialize the BoldDesk MCP Server via `mcp_server_tools` and pass the resulting tools to your assistant agents.

They can, but they should debate the changes first to prevent conflicts. Use one agent to fetch the ticket state with `get_ticket` and let another agent handle `update_ticket` only after they agree on the payload.

You assign different agents to different tasks. Your customer-facing agent uses `reply_to_ticket`, while your internal supervisor agent uses `add_ticket_note` to document their reasoning behind the scenes.

Your AutoGen agents should first run `list_agents` or `get_agent` to check availability. If the target agent is offline, the planning agents can debate alternative assignments before calling `update_ticket`.

Vinkius runs the integration inside an isolated, ephemeral V8 sandbox. Your support agent notes, customer contacts, and tickets are never stored on the platform, and all connection tokens are encrypted at rest.

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