How to Use the Chattermill MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK system read specific Chattermill responses?

Yes. The agent pulls a list of recent comments with listfeedbackresponses. It then inspects individual items using getresponsedetails to read the exact score and applied themes.

Q: How does the agent know which project to query in Chattermill?

It figures this out automatically. The system calls listchattermillprojects to find the correct project key, which is usually just the lowercase company name.

Build production-ready customer support agents that read and analyze Chattermill feedback using 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 Chattermill MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect the Chattermill MCP Server to production agents

Use `list_chattermill_projects` to grab your target project key directly from OpenAI. Your agent can pull exact sentiment scores and volume stats using `get_chattermill_metric` without writing custom API polling logic. Guardrails built into the framework ensure agents only request valid metric types like NPS or net_sentiment. Tracing comes for free. Every time your agent calls `list_feedback_responses` to read paginated customer comments, you track the exact date filters and page limits in your OpenAI dashboard. Handoffs work perfectly when a triage agent spots a tanking CSAT score and routes the data to a specialized retention agent.

Analyze themes and segments autonomously

Customer feedback gets messy fast. Your agent calls `list_feedback_themes` to pull machine-learning generated topics straight from the platform. It maps those topics to higher-level trends by hitting `list_theme_categories`. You don't have to hardcode segment IDs. The agent runs `list_custom_segments` to discover available cohorts dynamically. If it needs to drill down into a specific complaint, it fires `get_response_details` to read the raw comment, score, and applied metadata.

Submit new feedback via multi-agent flows

Ingesting data through a conversational interface happens in seconds. An ingestion agent takes user input and triggers `submit_feedback_response` with the required text and project key. It pulls valid source mappings beforehand using `list_feedback_sources` to ensure the Zendesk or App Store tag matches perfectly. Data types get validated before the payload leaves the server. The agent checks `list_data_types` to verify if the input should be tagged as a survey or review. You build reliable pipelines because the agent validates its own inputs against live Chattermill configurations.

Setup guide

Set up Chattermill 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 Chattermill tools at runtime.
3

Create your Agent

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

Run the agent

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

Run pip install openai-agents. Create an MCPServerStreamableHttp instance with your Vinkius endpoint URL and pass it into the mcp_servers list of your Agent constructor.

Yes. The agent pulls a list of recent comments with `list_feedback_responses`. It then inspects individual items using `get_response_details` to read the exact score and applied themes.

Not at all. The SDK auto-discovers all eleven tools exposed by the MCP Server. Set cacheToolsList to True to speed up initialization.

It figures this out automatically. The system calls `list_chattermill_projects` to find the correct project key, which is usually just the lowercase company name.

Your raw customer comments and NPS scores stay secure. The Vinkius V8 Isolate Sandbox destroys the environment immediately after the session ends. No persistent data remains on the MCP Server.

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