How to Use the Newton MCP in LlamaIndex

Q: How do I filter which math tools the agent accesses?

Use the allowedtools array in your setup. You restrict the agent to just mathabs and matharea if you want to prevent it from running unnecessary symbolic derivatives.

Ground your LlamaIndex RAG applications in exact mathematical reality by indexing symbolic computation results from 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 LlamaIndex

Create your Vinkius account to connect Newton to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index exact math with LlamaIndex

The Newton MCP Server feeds pure symbolic math directly into your searchable vectors. When your agent calls `math_derive`, LlamaIndex captures the exact algebraic output and stores it alongside your document nodes. You build RAG applications that query past calculations instead of recomputing them. If a user asks for the roots of a previously processed equation, the system pulls the exact array generated by `math_zeroes` directly from the index.

Process trigonometric queries

Newton provides a complete suite of trigonometric tools for spatial and geometric reasoning. Your agent executes `math_cos`, `math_sin`, and `math_tan` to calculate exact ratios based on user queries. You get inverse functions immediately. The `math_arccos`, `math_arcsin`, and `math_arctan` tools allow your application to derive angles from raw ratios, storing the step-by-step logic in your vector database.

Calculate complex logarithms

Look at how you handle scaling. The `math_log` tool accepts a base and a value to compute precise logarithmic scales. Your agent passes these two parameters to the server and receives the exact mathematical result. LlamaIndex uses this output to ground answers about exponential growth or decay. The exact values replace the LLM's tendency to hallucinate numbers when dealing with non-linear mathematical models.

Setup guide

Set up Newton MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Newton MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Newton tools.",
)
response = await agent.run("List recent Newton data")

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 LlamaIndex

Install llama-index-tools-mcp. Initialize a BasicMCPClient with the server URL, wrap it in an McpToolSpec, and call to_tool_list_async() before passing it to your FunctionAgent.

Yes. Because the framework indexes tool outputs, the results of `math_integrate` or `math_factor` become part of your queryable knowledge base.

The server processes any valid polynomial or trigonometric string you send. Extremely long strings hit standard execution timeouts, but the math engine handles standard advanced calculus without issue.

Use the allowed_tools array in your setup. You restrict the agent to just `math_abs` and `math_area` if you want to prevent it from running unnecessary symbolic derivatives.

The system only sees the literal math expression strings and base/value integers you transmit. Vinkius runs this MCP inside an ephemeral V8 Isolate, meaning your proprietary risk formulas vanish from memory the millisecond the computation 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