How to Use the CallRail MCP in OpenAI Agents SDK

Q: How do I connect CallRail to the OpenAI Agents SDK?

First, pip install openai-agents. Then create an MCPServerStreamableHttp instance pointed at your Vinkius endpoint for CallRail. The SDK discovers all the tools automatically.

Q: Can my agent see all my CallRail companies and users?

Yes. The listcompanies and listusers tools give your agent read-only access to that information. It can use this to get context before performing other tasks.

Q: What's the best way to use the CallRail MCP Server with the OpenAI Agents SDK for reporting?

Have your agent call listcalls and listformsubmissions with date ranges. The agent can then process the returned data to summarize performance, attribute leads to campaigns, and generate a report.

Build safe, production-ready marketing agents on CallRail with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect CallRail to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull your entire call and lead history

Give your agent direct access to your marketing performance data. It can run `list_calls` and `list_form_submissions` to get a raw feed of every interaction. No more downloading CSVs and parsing them by hand. From there, your agent can start to work. It can identify which campaigns are driving calls, spot high-value leads from form fills, or build daily performance reports. All actions are traced in the OpenAI dashboard, so you have a full audit log of what your agent did and what data it saw.

Get full context on accounts and companies

An agent needs context to do useful work. This MCP Server provides it. Your agent can start with `get_account_info` for a high-level view, then use `list_companies` to see every client you're tracking. Before taking an action, it can drill down with `get_company_details` to get specifics. The OpenAI Agents SDK is built for this kind of multi-step reasoning, with guardrails that can validate the agent's plan before it executes. You can build an agent that researches a company and then decides on a next step, safely.

Build a watchdog for your CallRail account

Use an agent to monitor your CallRail setup proactively. It can run on a schedule to check for issues before they become problems. You get an automated, reliable check on your marketing infrastructure. Have your agent call `list_alerts` to see if anything needs immediate attention. It can also use `list_trackers` to confirm all your phone numbers are configured correctly and `list_users` to audit who has access. Since it's all running through the OpenAI SDK, you get a clear trace of every check.

Setup guide

Set up CallRail MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all CallRail tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives CallRail tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate CallRail tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="CallRail Agent",
            instructions="You have access to CallRail tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

First, `pip install openai-agents`. Then create an `MCPServerStreamableHttp` instance pointed at your Vinkius endpoint for CallRail. The SDK discovers all the tools automatically.

Yes. The `list_companies` and `list_users` tools give your agent read-only access to that information. It can use this to get context before performing other tasks.

Have your agent call `list_calls` and `list_form_submissions` with date ranges. The agent can then process the returned data to summarize performance, attribute leads to campaigns, and generate a report.

Yes, you can configure the agent with a specific subset of tools if you don't want it to have access to everything. The OpenAI Agents SDK lets you define which functions are available during initialization.

No, it's a stateless proxy. When your OpenAI agent requests call logs or company details, the server fetches it from CallRail, sends it to your agent, and then forgets it. Vinkius runs these in ephemeral sandboxes for each request.

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