How to Use the Freshsuccess MCP in OpenAI Agents SDK

Q: How does OpenAI Agents SDK handle API connection failures with Freshsuccess?

The agent uses checkapistatus to verify the connection before starting a run. If the connection drops, the SDK's built-in error handling catches the failure, allowing your application to retry or fail gracefully without losing context.

Q: Is it possible to cache the tool list for faster agent execution?

Yes. Set cacheToolsList=True in your connection parameters. This prevents the SDK from querying the Vinkius endpoint for tool definitions on every single request, speeding up tools like listcustommetrics.

Get guardrailed OpenAI Agents SDK executions against Freshsuccess accounts without manual script writing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Freshsuccess MCP to OpenAI Agents SDK

Create your Vinkius account to connect Freshsuccess 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 Freshsuccess with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe account updates with OpenAI Agents SDK

Using `upsert_cs_account` and `upsert_cs_user`, you can deploy agents that modify customer records without worrying about them going rogue. When your agent attempts to update database fields, OpenAI's built-in guardrails validate the parameters before execution. This means your customer database stays clean and your automated workflows don't write garbage data. The agent reads real-time context from the Freshsuccess MCP Server to make decisions. If a customer health score drops, the agent triggers an internal alert or schedules a task. If it tries to write an invalid field, the SDK stops the execution immediately.

Automated health tracking and triage

With `get_account_health` and `list_cs_alerts`, you can run background agents that constantly check customer status without manual intervention. By polling these endpoints, your agent spots accounts that are slipping away. It then routes these alerts to the right human account manager before the customer churns. You can pass the server configuration straight into the Agent constructor using the streamable HTTP connection class. The agent auto-discovers these tools. This allows it to transition from analyzing usage trends to creating a follow-up task via `list_cs_tasks` in a single thread.

Custom telemetry updates in production

Logging telemetry data via `post_metric_value` keeps your customer success metrics updated directly from your application. Your agent uses this capability to write custom usage indicators. This keeps the health scores in your dashboard accurate and reflective of actual user behavior. Because the OpenAI Agents SDK supports full tracing, you can audit every single metric update in your OpenAI dashboard. You will see exactly why an agent chose to call `list_custom_metrics` and what values it recorded, making debugging straightforward.

Setup guide

Set up Freshsuccess 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 Freshsuccess tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and use the streamable HTTP server class to point to your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when initializing your Agent. The agent automatically discovers tools like `list_cs_accounts` at runtime.

Yes, you can control tool access by configuring the agent's system prompt or using specialized sub-agents. For instance, you can build a restricted agent that only has access to `get_user_health` and `list_cs_tasks` while blocking write operations.

The agent uses `check_api_status` to verify the connection before starting a run. If the connection drops, the SDK's built-in error handling catches the failure, allowing your application to retry or fail gracefully without losing context.

Yes. Set `cacheToolsList=True` in your connection parameters. This prevents the SDK from querying the Vinkius endpoint for tool definitions on every single request, speeding up tools like `list_custom_metrics`.

All communications run through Vinkius's zero-trust MCP gateway, meaning your API tokens and raw health metrics are never exposed to the LLM provider. Only the structured outputs of tools like `get_account_health` are passed to the agent, keeping your customer database isolated.

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