How do I find the Object Key for a specific table?

Use the `list_objects` tool. It will return all data objects in your application along with their names and unique keys (e.g., `object_1`). Use these keys for all subsequent record operations.

Can I search records using multiple conditions?

Yes. Use the `search_records` tool and provide a JSON array of filter objects. For example: `[{"field":"field_1", "operator":"is", "value":"active"}, {"field":"field_2", "operator":"contains", "value":"premium"}]`.

How do I know which fields to use when creating a record?

Use the `list_object_fields` tool with the target `object_key`. It will list all fields, their types, and their keys (e.g., `field_1`), which you must use as property names in your data JSON.

Knack MCP Server for AutoGen 10 tools — connect in under 2 minutes

Name: Knack
Availability: InStock
Author: Vinkius

microsoft.github.io/autogen/docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools Framework

Microsoft AutoGen enables multi-agent conversations where agents negotiate, delegate, and execute tasks collaboratively. Add Knack as an MCP tool provider through Vinkius and every agent in the group can access live data and take action.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.tools.mcp import McpWorkbench

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with McpWorkbench(
        server_params={"url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"},
        transport="streamable_http",
    ) as workbench:
        tools = await workbench.list_tools()
        agent = AssistantAgent(
            name="knack_agent",
            tools=tools,
            system_message=(
                "You help users with Knack. "
                "10 tools available."
            ),
        )
        print(f"Agent ready with {len(tools)} tools")

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Knack MCP Server

Connect your Knack application to any AI agent and take full control of your no-code database through natural conversation.

AutoGen enables multi-agent conversations where agents negotiate, delegate, and collaboratively use Knack tools. Connect 10 tools through Vinkius and assign role-based access. a data analyst queries while a reviewer validates, with optional human-in-the-loop approval for sensitive operations.

What you can do

Database Schema Discovery — List all objects and fields to understand your data structure without leaving the chat
Record Management — Create, retrieve, update, and delete records in any object securely
Advanced Querying — Search for specific records using complex filters based on any field criteria
Data Auditing — Get detailed summaries of specific records to verify information or track changes
Bulk Operations — Effortlessly manage multiple records by providing structured data to your agent

The Knack MCP Server exposes 10 tools through the Vinkius. Connect it to AutoGen in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Knack to AutoGen via MCP

Follow these steps to integrate the Knack MCP Server with AutoGen.

Install AutoGen

Run pip install "autogen-ext[mcp]"

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Integrate into workflow

Use the agent in your AutoGen multi-agent orchestration

Explore tools

The workbench discovers 10 tools from Knack automatically

Why Use AutoGen with the Knack MCP Server

AutoGen provides unique advantages when paired with Knack through the Model Context Protocol.

Multi-agent conversations: multiple AutoGen agents discuss, delegate, and collaboratively use Knack tools to solve complex tasks

Role-based architecture lets you assign Knack tool access to specific agents. a data analyst queries while a reviewer validates

Human-in-the-loop support: agents can pause for human approval before executing sensitive Knack tool calls

Code execution sandbox: AutoGen agents can write and run code that processes Knack tool responses in an isolated environment

Knack + AutoGen Use Cases

Practical scenarios where AutoGen combined with the Knack MCP Server delivers measurable value.

Collaborative analysis: one agent queries Knack while another validates results and a third generates the final report

Automated review pipelines: a researcher agent fetches data from Knack, a critic agent evaluates quality, and a writer produces the output

Interactive planning: agents negotiate task allocation using Knack data to make informed decisions about resource distribution

Code generation with live data: an AutoGen coder agent writes scripts that process Knack responses in a sandboxed execution environment

Knack MCP Tools for AutoGen (10)

These 10 tools become available when you connect Knack to AutoGen via MCP:

create_record

You must provide the data as a JSON string where keys are the field keys (e.g., field_1). Ensure you have checked the object schema first to know which fields are required. Create a new record in a Knack object

delete_record

Use with caution as this action cannot be undone. Delete a record from a Knack object

get_object_schema

Returns metadata including the object name, key, and high-level structure. Use this to verify you are working with the correct database table. Get the schema of a specific Knack object

get_record

Requires both the object_key and the record_id. Use this for detailed auditing of a specific entry. Get a specific record by ID

list_account_applications

Use this to verify access or discover application IDs. List all applications in the account

list_object_fields

This is crucial for understanding the data types and identifying the field keys (field_1, field_2, etc.) needed for creating or updating records. List all fields for a specific Knack object

list_objects

This is the first step to understand the database structure and find the "Object Key" needed for record operations. List all objects in the Knack application

list_records

You must provide the object_key. Use this to browse the actual data stored in your database. List records for a specific Knack object

search_records

The filters must be provided as a JSON string following the Knack Filter format (e.g., "[{\"field\":\"field_1\", \"operator\":\"is\", \"value\":\"test\"}]"). Search for records using filters

update_record

Provide only the fields you wish to change in the JSON string data. This is a partial update. Update an existing record in a Knack object

Example Prompts for Knack in AutoGen

Ready-to-use prompts you can give your AutoGen agent to start working with Knack immediately.

"List all database objects in my Knack app"

"Find all premium customers in 'object_1'"

"Create a new customer in 'object_1' with name 'Sarah' and email 'sarah@example.com'"

Troubleshooting Knack MCP Server with AutoGen

Common issues when connecting Knack to AutoGen through the Vinkius, and how to resolve them.

McpWorkbench not found

Install: pip install "autogen-ext[mcp]"

Knack + AutoGen FAQ

Common questions about integrating Knack MCP Server with AutoGen.

How does AutoGen connect to MCP servers?

Create an MCP tool adapter and assign it to one or more agents in the group chat. AutoGen agents can then call Knack tools during their conversation turns.

Can different agents have different MCP tool access?

Yes. AutoGen's role-based architecture lets you assign specific MCP tools to specific agents, so a querying agent has different capabilities than a reviewing agent.