How to Use the Newton MCP in AutoGen

Q: How do I load the Newton MCP Server into AutoGen?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams to fetch the tool definitions, then pass the list to your AssistantAgent constructor.

Deploy the Newton MCP Server in AutoGen to give your debating agents a deterministic mathematical referee for complex symbolic calculations.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Newton MCP to AutoGen

Create your Vinkius account to connect Newton 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 Newton with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Settle debates with the MCP Server

Start with the facts. Newton acts as the absolute source of truth for your AutoGen conversational agents. When an engineering agent and a finance agent disagree on a growth curve, one of them calls `math_integrate` to prove their point with exact calculus. The result forces consensus. Instead of arguing over approximated numbers, the agents receive deterministic output from tools like `math_area` and adjust their next arguments based on hard mathematical facts.

Analyze function behavior

The `math_tangent` tool requires both an x-value and a function expression to calculate precise tangent lines. Your mathematical agents use this to evaluate the rate of change at specific points in a model. Agents verify these findings by cross-referencing other tools. A checker agent runs `math_derive` on the same core expression to ensure the derived slope matches the tangent line output.

Standardize math across agents

The `math_simplify` tool ensures all agents in the chat speak the same mathematical language. When one agent generates a messy polynomial, another agent reduces it before continuing the conversation. This prevents compounding errors during multi-turn debates. By constantly running `math_factor` and simplification tools, the agent swarm keeps the underlying equations clean and mathematically sound.

Setup guide

Set up Newton 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 Newton 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="Newton_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install autogen-ext[mcp]. Use mcp_server_tools with StreamableHttpServerParams to fetch the tool definitions, then pass the list to your AssistantAgent constructor.

Yes. The McpToolAdapter handles all schema translation in the background. Your agents see native JSON structures for inputs like `math_abs` and `math_zeroes`.

The framework queues tool execution based on the conversation turn. Only the agent currently holding the speaking turn can trigger the MCP Server to perform a calculation.

You must include instructions in the agent's system prompt. Tell them to use the (over) keyword when formatting numerators and denominators for the simplification tool.

The engine reads raw algebraic strings and numeric variables, nothing else. Every calculation executes in a zero-trust V8 sandbox that terminates immediately, ensuring your core algorithmic logic never persists on disk.

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