How to Use the Observe.AI MCP in OpenAI Agents SDK

Q: How do I connect the Observe.AI MCP Server to the OpenAI Agents SDK?

Install the package with pip install openai-agents and instantiate the server using your Vinkius endpoint. Pass the server instance directly to your agent's constructor to auto-discover tools like listinteractions.

Q: Can an Observe.AI agent in the OpenAI Agents SDK run evaluations automatically?

Yes, your agent can pull active grading rubrics via listevaluationforms and submit scores. The SDK's built-in validation guardrails ensure the agent doesn't submit corrupt or incomplete evaluations.

Q: Does my raw call transcript data remain secure?

Your raw call transcripts retrieved via getinteractiontranscript are processed inside isolated, ephemeral Vinkius sandboxes. No data is stored on Vinkius, and the OpenAI Agents SDK communicates over encrypted, single-token HTTP channels to keep customer conversations private.

Feed raw contact center transcripts and QA metrics directly into your OpenAI Agents SDK pipeline with zero manual setup.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Observe.AI MCP to OpenAI Agents SDK

Create your Vinkius account to connect Observe.AI 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 Observe.AI with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run automated QA audits using this MCP Server

Stop wasting hours listening to call recordings. Your OpenAI agent uses `list_interactions` to target low-performing calls and pulls the exact text with `get_interaction_transcript`. The SDK's built-in guardrails validate every step before saving, keeping things accurate. You get direct access to `list_evaluation_forms` so the agent scores calls against your actual rubrics. The OpenAI dashboard traces the entire run, showing you exactly how the agent graded the interaction before it commits the final QA evaluation.

Target coaching opportunities with OpenAI agents

Let your agent track performance trends over time. By combining `list_coaching_sessions` with `list_qa_evaluations`, the agent identifies which support reps are struggling and schedules targeted follow-ups. The OpenAI Agents SDK manages handoffs between specialized agents. One agent flags compliance issues via `list_interaction_moments`, while the other pulls `list_workspace_users` to assign a human supervisor for 1-on-1 training.

Extract immediate summaries from customer calls

Get straight to the point of customer disputes without reading endless text blocks. The agent calls `list_interaction_summaries` to fetch call recaps, then uses `get_interaction_details` to isolate the exact timestamp of the complaint. This MCP Server runs inside Vinkius's secure sandbox, feeding clean call data straight to your OpenAI Agents SDK pipelines. You get structured, auditable outputs without risking raw data exposure to unverified third-party tools.

Setup guide

Set up Observe.AI 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 Observe.AI tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with `pip install openai-agents` and instantiate the server using your Vinkius endpoint. Pass the server instance directly to your agent's constructor to auto-discover tools like `list_interactions`.

Yes, your agent can pull active grading rubrics via `list_evaluation_forms` and submit scores. The SDK's built-in validation guardrails ensure the agent doesn't submit corrupt or incomplete evaluations.

You can design a multi-agent system where a triage agent scans calls using `list_interaction_moments` and hands off to a coaching agent. The coaching agent then uses `list_coaching_sessions` to log specific training tasks using this MCP integration.

You control this by managing permissions on the Vinkius platform. When the agent calls `list_workspace_users`, it only receives the specific agent profiles allowed by your token.

Your raw call transcripts retrieved via `get_interaction_transcript` are processed inside isolated, ephemeral Vinkius sandboxes. No data is stored on Vinkius, and the OpenAI Agents SDK communicates over encrypted, single-token HTTP channels to keep customer conversations private.

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