How to Use the KnowFirst MCP in AutoGen

Q: Can a human participate in the AutoGen agent conversation?

Yes. You can set up a UserProxyAgent that allows you to step in, provide feedback, and guide the conversation. If your agents get stuck analyzing KnowFirst data, you can give them the next step.

Q: Does using KnowFirst with AutoGen require a lot of boilerplate code?

No, the autogen-extmcp package simplifies it. The mcpservertools function fetches and prepares all the KnowFirst tools, and the McpToolAdapter handles converting the data for the agents automatically.

Build teams of AutoGen agents that debate market signals from KnowFirst, reaching a consensus before taking action.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KnowFirst MCP to AutoGen

Create your Vinkius account to connect KnowFirst 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 KnowFirst with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assemble an AI Research Team

Go beyond a single agent. With AutoGen, you create a group of specialized agents that collaborate using KnowFirst data. A 'Researcher' agent can `search_intelligence_entities` and `get_entity_profile`, passing the findings to an 'Analyst' agent for interpretation. The Analyst might then use `get_entity_connections` to map relationships, while a 'Skeptic' agent double-checks the findings by calling `list_intelligence_sources`. The final output isn't one agent's opinion; it's a conclusion they all agreed on.

Use AutoGen for Consensus-Driven Analysis

Let your agents argue. One agent might call `get_market_intelligence_trends` and suggest a bullish outlook. Another agent can challenge that by using `audit_entity_changes` on key companies to find negative signals. This debate happens automatically in the background. This process surfaces risks a single agent might miss. You're building a system that models a real-world analyst team meeting. The conversation continues until the agents converge on a course of action, like executing a specific `query_custom_intelligence` for more detail. This is a powerful MCP Server for multi-agent systems.

Automate Complex Due Diligence

Assign roles for a thorough investigation. A 'Compliance' agent could be responsible for running `audit_entity_changes` on a target company. Meanwhile, a 'Strategy' agent uses `get_market_intelligence_trends` to evaluate the broader market context. The agents present their findings to a 'Manager' agent, which can ask for clarification or request more data, perhaps by telling another agent to run a `search_data_sources` query. You get a detailed report that's been reviewed from multiple angles, all orchestrated by AutoGen.

Setup guide

Set up KnowFirst 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 KnowFirst 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="KnowFirst_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You create separate tool lists from the KnowFirst MCP server and pass them to each `AssistantAgent` during initialization. This lets you create specialized agents, like one that can only read data and another that can perform audits.

Yes. You can set up a `UserProxyAgent` that allows you to step in, provide feedback, and guide the conversation. If your agents get stuck analyzing KnowFirst data, you can give them the next step.

No, the `autogen-ext[mcp]` package simplifies it. The `mcp_server_tools` function fetches and prepares all the KnowFirst tools, and the `McpToolAdapter` handles converting the data for the agents automatically.

The conversation itself is the log. Each agent's turn, including which tool it calls (`get_entity_profile`, for example) and the result it gets, is printed out. You can watch the entire analytical debate unfold in your terminal.

Yes. Each agent's request for data like entity connections or raw data points is handled through your single Vinkius endpoint. The data is transmitted securely and processed in a temporary, single-tenant environment that is wiped clean after use. Vinkius has no visibility into the content of your agent's queries.

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