How to Use the CallRail MCP in AutoGen

Q: How do I add CallRail tools to AutoGen agents?

Install autogen-extmcp and use mcpservertools with your Vinkius HTTP endpoint. Pass the resulting CallRail MCP Server tool list directly into your AssistantAgent constructor.

Q: Can multiple AutoGen agents use CallRail simultaneously?

Yes. The McpToolAdapter automatically manages schema conversions so any agent in your chat room can invoke the tracking tools when they need evidence.

Deploy AutoGen multi-agent squads to debate CallRail marketing attribution and audit tracking numbers automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CallRail MCP to AutoGen

Create your Vinkius account to connect CallRail 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 CallRail with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

CallRail MCP Server Auditing

An analyst agent runs `list_calls` to pull recent inbound volume, while a compliance agent reviews the output for missing tracking sources. AutoGen setups thrive on competing perspectives, and this integration gives them raw marketing data to argue over. They debate the discrepancies until they reach a consensus on campaign performance. You just provide the tools via `mcp_server_tools`, and the agents negotiate the best way to interpret `get_call_details` outputs.

Consensus-Driven Lead Scoring

Equipping your AutoGen squad with `list_form_submissions` lets multiple agents review the exact same inbound inquiries from different angles. Scoring web leads is subjective when done by a single LLM. A sales-focused agent argues for immediate outreach based on form content, while a marketing agent checks `list_tags` to verify the campaign source. They deliberate until they agree on a final lead score, producing a much more reliable result.

Monitor Agency Accounts

You assign an infrastructure agent to run `list_alerts` and `list_trackers` on a loop to find disconnected phone numbers. Complex agency setups break constantly without anyone noticing. When it finds a broken tracker, it notifies an account manager agent. The second agent pulls the client context using `get_company_details` and drafts an alert email, proving the value of autonomous systems working in tandem.

Setup guide

Set up CallRail 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 CallRail 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="CallRail_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your Vinkius HTTP endpoint. Pass the resulting CallRail MCP Server tool list directly into your AssistantAgent constructor.

Yes. The `McpToolAdapter` automatically manages schema conversions so any agent in your chat room can invoke the tracking tools when they need evidence.

The agents read the API response and discuss whether they need more data. If a list is truncated, they independently decide to call the tool again with updated parameters.

You assign the server solely to a designated data-gathering agent. Other agents in the conversation must ask the data gatherer to pull tracking metrics for them.

Vinkius proxies the requests through a stateless, zero-trust connection. Your inbound call logs and caller ID data never touch our disks, maintaining strict privacy for your marketing clients.

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