How to Use the Knack MCP in AutoGen

Q: What tool should my agent use to see all the tables in my database?

Use the listobjects tool. It returns a list of all available objects in your Knack application, which is the right starting point for any database exploration task.

Deploy teams of AutoGen agents that debate and manage your Knack database collaboratively.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knack MCP to AutoGen

Create your Vinkius account to connect Knack 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 Knack with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Record Updates

Imagine a data quality team of agents. One agent, the "Auditor," uses `search_records` to find entries with missing data. It proposes an update to a second agent, the "Enricher," which might use external tools to find the missing info. After they agree on the data, a third "Executor" agent calls `update_record` to apply the change in Knack. The action only happens after the agents reach a consensus on the correct data, which prevents bad writes.

Debate Schema Changes Before Action

When you need to add data, you can have agents discuss the best approach. A "Planner" agent might use `list_objects` and `get_object_schema` to analyze the existing database structure. It then suggests creating a record in a specific object. A "Critic" agent can challenge this, arguing that a different object is a better fit. They debate until they agree. Only then does an agent call `create_record`. This MCP server setup stops data from being added to the wrong place.

Safe Deletion with Multi-Agent Review

Deleting data is risky. With AutoGen, you build a safety net. An agent can propose deleting a record by its ID, but it can't execute the call directly. Instead, it passes the proposal to a "Human-in-the-loop" agent. This triggers a confirmation prompt for a real person to approve or deny the request. Only with explicit approval does the "Executor" agent get the green light to call `delete_record`. It gives your agent team the power to act, but with critical human oversight.

Setup guide

Set up Knack 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 Knack 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="Knack_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Set up a multi-agent conversation. One agent proposes the deletion, and another agent requires human confirmation before the `delete_record` tool is actually called. This workflow prevents accidental data loss.

Yes, that's a primary AutoGen pattern. A 'Researcher' agent can use `search_records` to find the data. It then passes the record ID and proposed changes to an 'Executor' agent, which calls `update_record`.

You'd assign one agent the role of 'DB Analyst.' Its job is to use the `list_objects` and `list_object_fields` tools and share the results with the other agents, ensuring the entire team is working with an accurate schema map.

Use the `list_objects` tool. It returns a list of all available objects in your Knack application, which is the right starting point for any database exploration task.

Your AutoGen agents don't get direct database access. They communicate with the Vinkius MCP server, which translates their requests into specific Knack API calls. All processing of your application and record data happens in a sandboxed session that's destroyed after the task is complete.

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