How to Use the Newton MCP in CrewAI

Equip your CrewAI quantitative agents with exact symbolic mathematics using the Newton MCP server.

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 CrewAI

Create your Vinkius account to connect Newton to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Give quantitative agents exact math tools

Newton equips your CrewAI teams with tools like `math_derive` and `math_integrate` so specialized agents can perform exact symbolic calculus. You assign these capabilities to a dedicated mathematician agent while keeping your researcher and writer agents focused on text processing. Language models fail at complex algebra. By passing mathematical operations to this server, your autonomous crew relies on a deterministic engine. The math agent solves the equation and passes the verified result to the analyst agent for reporting.

Factor polynomials autonomously via MCP Server

The `math_factor` and `math_zeroes` tools allow your agents to break down equations and locate exact roots without human intervention. A data extraction agent pulls a formula from a database, hands it to the math persona, and gets a structured array of zeroes in return. You dictate the sequence. The execution flow guarantees that downstream agents only receive mathematically proven simplified expressions via `math_simplify`. This prevents hallucinated numbers from corrupting your final outputs.

Compute areas and tangent lines

Agents calculate the area under a curve using the `math_area` tool by providing the function and the bounds. For linear approximations, they hit the `math_tangent` endpoint with a specific x-value to get the exact tangent line. The server handles standard trigonometric operations as well. Tools like `math_arcsin` and `math_cos` give your crew everything they need to process geometric data autonomously. Every MCP tool call executes in isolation.

Setup guide

Set up Newton MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Newton tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Newton Analyst",
    goal="Access and analyze Newton data via MCP.",
    backstory="Expert analyst with direct Newton access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Newton transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Newton Analyst",
        goal="Access and analyze Newton data via MCP.",
        backstory="Expert analyst with direct Newton access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Newton transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL into the mcps array when defining your agent. The framework automatically discovers the math tools and makes them available to that specific persona.

Yes. You can bind the same MCP endpoint to multiple agents, or restrict it to a single quantitative persona using the tool_filter parameter.

Complex symbolic integration takes processing time. We recommend running the math agent asynchronously if the rest of your crew needs to continue working while the calculation runs.

The tool descriptions explicitly tell the agent to use the (over) keyword for division. The LLM reads this schema and formats the request correctly before execution.

We process your mathematical formulas and numeric parameters in memory. The zero-trust architecture ensures that all variables and expressions vanish completely after the calculation finishes.

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