How to Use the Gainsight CS MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK work with Gainsight CS to find at-risk customers?

Your agent uses listcallstoaction to get a list of all open CTAs. It can then use getctametadata to dig into the specifics of each one, like its priority and due date, to flag the most critical issues for your team.

Q: Can I use the OpenAI Agents SDK to automate reporting from Gainsight CS?

Yes. You can build an agent that periodically calls listcockpittasks and listtimelineevents for a specific company. It can then format that data into a summary and send it to your team on a schedule.

Build production-ready CS agents that manage Gainsight timelines and health scores, all within the safety of 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 Gainsight CS MCP to OpenAI Agents SDK

Create your Vinkius account to connect Gainsight CS 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 Gainsight CS with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Timeline Entries

Give your agent the `log_timeline_activity` tool and let it handle the busywork of recording customer interactions. Because the OpenAI SDK automatically discovers every tool on this MCP server, your agent knows exactly what's possible from the start. With built-in guardrails, you can let agents run without constant supervision. The framework validates the agent's intended action before it ever hits the Gainsight API, preventing bad data from ever being written. It's how you move from prototype to a deployed CS automation product.

Triage Customer Health

Create specialized agents that hand off tasks for a complete picture of customer health. One agent can run `list_calls_to_action` to spot at-risk accounts, then pass the company ID to another agent to pull details with `get_company_health`. This isn't just a simple script. You're building a system where each agent has a specific job. The full execution trace in the OpenAI dashboard shows you every step, from the initial query to the final API call, making it easy to debug and prove reliability.

Your Gainsight CS MCP Server

Connect your Python code to Gainsight CS in minutes. The `MCPServerStreamableHttp` client handles the connection, and setting `cacheToolsList=True` means your agent doesn't have to re-discover tools on every run. It's fast and efficient. Your agent can even check its own identity and permissions with `get_my_identity` before trying to perform an action. This self-awareness, combined with the secure connection provided by the MCP server, means you're building robust, security-conscious automations.

Setup guide

Set up Gainsight CS 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 Gainsight CS tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Gainsight CS 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="Gainsight CS Agent",
            instructions="You have access to Gainsight CS 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 Gainsight CS. 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 Gainsight CS 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 Gainsight CS MCP in OpenAI Agents SDK

Your agent uses `list_calls_to_action` to get a list of all open CTAs. It can then use `get_cta_metadata` to dig into the specifics of each one, like its priority and due date, to flag the most critical issues for your team.

Yes. You can build an agent that periodically calls `list_cockpit_tasks` and `list_timeline_events` for a specific company. It can then format that data into a summary and send it to your team on a schedule.

It is. The OpenAI Agents SDK has guardrails that let you approve or deny an agent's plan before it runs `log_timeline_activity`. You have full control over what gets written to your customer records.

It's a simple health check. Your agent can call it on startup to make sure it can actually talk to the Gainsight API before it starts any real work. It's a basic but crucial step for reliable automation.

This server only interacts with Gainsight CS objects like company metadata, person details, and timeline activities. Your Vinkius endpoint token is the only credential needed, and all requests are processed in an ephemeral, zero-trust sandbox.

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