How to Use the Chaindesk MCP in AutoGen

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

Install autogen-extmcp and use the mcpservertools helper with your Vinkius server URL. Pass the resulting tool list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents query the same Chaindesk datastore?

Yes, any agent in your group conversation can call getdatastore or queryagent as long as they have access to the tool list. This allows collaborative search and verification.

Q: How does AutoGen handle schema conversion for Chaindesk?

The McpToolAdapter inside the AutoGen extension automatically translates the server's schemas into the JSON format required by the LLM. You do not need to write any manual validation code.

Q: Can I filter active conversations by agent?

Yes, you can use listconversations and pass a specific agentId filter. This lets your coordinator agent analyze the chat history of a single bot without pulling unrelated logs.

Q: How does this server protect customer chat logs?

All chat data pulled via getmessages is fetched through secure HTTPS connections directly to Chaindesk. Vinkius runs this MCP Server in an ephemeral, zero-trust sandbox that destroys all session data upon execution.

Let your AutoGen agents debate and manage Chaindesk knowledge bases using 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 Chaindesk MCP to AutoGen

Create your Vinkius account to connect Chaindesk 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 Chaindesk with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

AutoGen consensus on support tickets

Build a team of AutoGen agents that collaborate before replying to a customer using `query_agent` over this MCP Server. One agent can fetch context using `get_messages`, while a second agent calls the query tool to test potential responses. They debate the quality of the answer in a loop. Once they agree on the best response, a third agent updates the central knowledge base using `upsert_datasource` to log the approved resolution.

Programmatic agent deployments

Let your AutoGen coordinator agent spin up specialized workers on demand using `create_agent`. Your manager script deploys a fresh support bot with a specific system prompt and datastore ID. When the task is finished, the coordinator cleans up the environment using `delete_agent`. This keeps your operational costs low and your workspace clean.

Real-time datastore audits

Use a dedicated auditor agent to monitor your knowledge bases with `list_datastores`. The agent calls this tool and `get_datastore` to check which files are currently indexed. If the auditor detects outdated files, it triggers `upsert_datasource` to overwrite them. It ensures your customer support bots never give answers based on expired documentation.

Setup guide

Set up Chaindesk 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 Chaindesk 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="Chaindesk_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use the `mcp_server_tools` helper with your Vinkius server URL. Pass the resulting tool list directly into your `AssistantAgent` constructor.

Yes, any agent in your group conversation can call `get_datastore` or `query_agent` as long as they have access to the tool list. This allows collaborative search and verification.

The `McpToolAdapter` inside the AutoGen extension automatically translates the server's schemas into the JSON format required by the LLM. You do not need to write any manual validation code.

Yes, you can use `list_conversations` and pass a specific `agentId` filter. This lets your coordinator agent analyze the chat history of a single bot without pulling unrelated logs.

All chat data pulled via `get_messages` is fetched through secure HTTPS connections directly to Chaindesk. Vinkius runs this MCP Server in an ephemeral, zero-trust sandbox that destroys all session data upon execution.

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