How to Use the Numbers API MCP in AutoGen

Q: How do I add the Numbers API to my AutoGen agent group?

You configure the StreamableHttpServerParams with your Vinkius URL and pass the tools to your AssistantAgent constructor. This makes all five numeric tools available to every agent in your conversation.

Q: Can multiple AutoGen agents call the Numbers API simultaneously?

Yes, the agents can call tools like getmathfact or getyearfact independently during their debate. The server handles concurrent requests smoothly, allowing your agents to deliberate without bottlenecking.

Let your AutoGen agents debate mathematical and historical facts with real-time data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Numbers API MCP to AutoGen

Create your Vinkius account to connect Numbers API 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 Numbers API with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve agent debates with real math facts

`get_math_fact` provides the objective mathematical truth needed to resolve conflicts between debating AutoGen agents. When a math agent and a critic agent disagree on a number's properties, they call this tool to settle the debate with hard data. You register this tool using `mcp_server_tools` to expose the endpoint to your agent group. This consensus-driven setup ensures that your automated workflows are grounded in verified mathematical properties.

Ground historical conversations using this MCP Server

This MCP Server allows your AutoGen agents to verify historical timelines using `get_year_fact` and `get_date_fact`. Instead of guessing historical events, your agents query these tools to build a shared chronological timeline. One agent can fetch a date fact while another validates the historical context of that year. This multi-agent collaboration prevents incorrect dates from corrupting the conversation history.

Inject random trivia into multi-agent workflows

To break deadlocks in creative agent conversations, `get_trivia_fact` and `get_random_fact` supply unexpected numeric trivia. Agents use these tools to introduce unique historical or mathematical associations into their deliberation loops. The MCP tool adapter handles the schema conversion automatically, making these endpoints instantly compatible with your assistant agents. This allows for rapid iteration during complex multi-agent simulations.

Setup guide

Set up Numbers API 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 Numbers API 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="Numbers API_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You configure the `StreamableHttpServerParams` with your Vinkius URL and pass the tools to your `AssistantAgent` constructor. This makes all five numeric tools available to every agent in your conversation.

Yes, the agents can call tools like `get_math_fact` or `get_year_fact` independently during their debate. The server handles concurrent requests smoothly, allowing your agents to deliberate without bottlenecking.

The MCP tool adapter automatically translates the server's tool definitions into the JSON schema format that AutoGen expects. You do not need to write any custom parsing code to get date or math facts.

Yes, this MCP adapter supports both stdio and HTTP transports. You can run the server locally or connect to the managed Vinkius hosting using standard connection parameters.

All queried integers, years, and dates are processed inside a zero-trust, ephemeral V8 sandbox on Vinkius. No agent conversation history or context is leaked to the external API, ensuring your multi-agent system remains secure.

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