How to Use the Attio MCP in OpenAI Agents SDK

Q: Attio OpenAI Agents SDK setup guide

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Vinkius URL, then pass it to the mcpservers array in your Agent constructor.

Q: OpenAI Agents SDK custom objects in Attio

Yes, custom tables work out of the box. The agent calls listobjects to discover standard and custom tables, mapping the schema automatically.

Q: Attio OpenAI Agents SDK tool caching

You need to set cacheToolsList=True in your server parameters. That stops the agent from refetching the tool definitions on every single startup.

Q: Check connection status

Run the getaccountcheck tool. It returns a quick status confirming your workspace token is valid and the MCP endpoint is active.

Connect the Attio MCP Server to your OpenAI Agents SDK production builds. Auto-discover CRM tools and validate agent actions before execution.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Attio MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Auto-discovered MCP Server tools for CRM

You drop the Vinkius endpoint into your OpenAI Agents SDK configuration and the tools map themselves. Your agent immediately knows how to read your workspace tables using `list_objects` and inspect the columns with `list_attributes`. No manual schema definitions required. The agent constructor handles the heavy lifting. Setting `cacheToolsList=True` speeds up initialization, preparing your system to read or write CRM data instantly. Handoffs between specialized sales agents work natively with these exposed endpoints.

Guardrailed CRM updates

Modifying production sales data requires strict boundaries. When your agent decides to update a deal stage, it calls `assert_record`. Built-in SDK guardrails catch the payload before execution, ensuring the agent does not wipe out critical account information by mistake. Creating new entries follows the exact same path. The `create_record` tool accepts the validated payload and pushes it directly to Attio. You track the entire decision tree inside the OpenAI dashboard, tracing exactly why the agent made that specific update.

Deep workspace querying

Sometimes your agent needs specific context before taking action. It runs `query_records` to pull active deals or filter accounts by revenue. The SDK feeds this data back into the context window for further reasoning and planning. If the exact ID remains unknown, the agent falls back to `search_records`. This global fuzzy search spans all objects in your workspace. It finds the right contact or company, grabs the ID, and proceeds with the assigned task.

Setup guide

Set up Attio 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 Attio tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius URL, then pass it to the `mcp_servers` array in your Agent constructor.

Yes, custom tables work out of the box. The agent calls `list_objects` to discover standard and custom tables, mapping the schema automatically.

You need to set `cacheToolsList=True` in your server parameters. That stops the agent from refetching the tool definitions on every single startup.

Run the `get_account_check` tool. It returns a quick status confirming your workspace token is valid and the MCP endpoint is active.

Every request runs inside an ephemeral V8 Isolate sandbox. Your sales pipelines, deal values, and contact emails never touch a persistent disk. Vinkius authenticates the request, executes the query, and destroys the sandbox instantly.

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