How to Use the NumVerify MCP in AutoGen

Q: How do I register the NumVerify MCP Server in AutoGen?

Install autogen-extmcp via pip. Use mcpservertools with your server's HTTP URL, and pass the resulting tools list directly to your AssistantAgent constructor.

Q: Can AutoGen agents verify phone line types with NumVerify?

Yes, agents call getphonelinetype during their conversational loop. A security agent can share the line type output with a database agent to decide if a record needs updating.

Q: How do AutoGen agents handle NumVerify validation errors?

If validatephone returns an error, the executing agent shares the failure message with the group. The coordinator agent then instructs the user-facing agent to prompt the user for a corrected format.

AutoGen agents debate phone validity and carrier risks before updating your systems.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect NumVerify MCP to AutoGen

Create your Vinkius account to connect NumVerify 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 NumVerify with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let agents debate phone risk using `validate_phone`

The `validate_phone` tool provides structural validation and carrier metadata for any phone number. In an AutoGen setup, a security agent runs this tool to check incoming signups. It then passes the output to a compliance agent to decide if the user is high-risk. If the number is flagged as invalid, the agents debate whether to block the registration or request an alternative contact method. This automated conversation ensures that only valid, high-quality numbers get written to your database.

Block VoIP fraud using `get_phone_line_type`

The `get_phone_line_type` tool identifies virtual numbers, landlines, and mobile phones. A fraud-detection agent uses this tool to flag VoIP numbers, which are often used for bulk spam signups. The fraud agent presents its findings to a product agent. They negotiate whether to allow the signup with extra verification or block it entirely. This consensus-driven approach keeps your user base clean without requiring manual review.

Route leads via this MCP Server

This MCP Server helps agents determine where a user is located and who provides their phone service. The `get_phone_location` tool extracts geographic data, while `get_phone_carrier` identifies the network provider. Your sales routing agent and support routing agent discuss these details to assign the lead. They look at the geographic region and carrier to determine the best agent to handle the account, resolving any assignment conflicts automatically.

Setup guide

Set up NumVerify 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 NumVerify 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="NumVerify_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` via pip. Use `mcp_server_tools` with your server's HTTP URL, and pass the resulting tools list directly to your `AssistantAgent` constructor.

Yes, agents call `get_phone_line_type` during their conversational loop. A security agent can share the line type output with a database agent to decide if a record needs updating.

If `validate_phone` returns an error, the executing agent shares the failure message with the group. The coordinator agent then instructs the user-facing agent to prompt the user for a corrected format.

Yes, the adapter supports both transport types. You can configure your connection depending on whether you run the server locally or host it on Vinkius.

Yes, phone numbers and carrier metadata are only passed within the active agent session. The Vinkius gateway handles authorization using a single secure token, ensuring phone queries are encrypted and never stored.

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