How to Use the Knorish MCP in AutoGen

Q: How do I configure Knorish for AutoGen?

Install autogen-extmcp. Load the tools via mcpservertools with your HTTP parameters, and hand that list to your AssistantAgent.

Q: How do multiple AutoGen agents share Knorish data?

One agent fetches the data using getuser and drops it into the shared conversation history. The other agents read that context and respond accordingly.

Deploy debating AutoGen agents to manage your Knorish school operations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Knorish MCP to AutoGen

Create your Vinkius account to connect Knorish 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 Knorish with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent enrollment consensus

Complex refund requests shouldn't rely on a single script, so you assign agents to debate before touching `unenroll_user`. With the Knorish MCP Server, one AutoGen agent reviews policy while another executes changes. The execution agent proposes a fix. The policy agent checks `get_student_progress` to verify the student hasn't exceeded the refund window. Only after they reach an agreement does the system process the removal.

AutoGen MCP Server catalog audits

Finding pricing errors requires multiple perspectives, which is why a sales agent pulls active inventory using `list_bundles`. A finance agent cross-references those prices against your marketing copy. If they find a mismatch, they flag it immediately. The agents negotiate the severity of the error based on the `get_account_info` data and generate a prioritized alert for your human team.

Webhook security reviews

Opening endpoints always introduces risk, so a security agent intercepts any request to fire `create_webhook`. It reviews the target URL and payload structure before anything goes live. The security agent might demand changes. It runs `list_webhooks` to see if a similar integration already exists. This adversarial approach prevents duplicate or unsafe data pipelines from reaching production.

Setup guide

Set up Knorish 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 Knorish 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="Knorish_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]`. Load the tools via `mcp_server_tools` with your HTTP parameters, and hand that list to your `AssistantAgent`.

Yes. Once the agents reach consensus, the designated execution agent calls `enroll_user` with the agreed-upon user and course IDs.

One agent fetches the data using `get_user` and drops it into the shared conversation history. The other agents read that context and respond accordingly.

You define strict system prompts and require human-in-the-loop approval for destructive actions. The MCP tools only propose the API calls.

AutoGen handles personally identifiable information like user emails and course progress. Vinkius secures this by routing all requests through a stateless, zero-trust sandbox that destroys the environment instantly after 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