4,500+ servers built on MCP Fusion
Vinkius
Crisp logo
Vinkius
OpenAI Agents SDK logo

How to Use the Crisp MCP in OpenAI Agents SDK

Build production-ready support agents for Crisp with the OpenAI Agents SDK. Guardrails and tracing come standard.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Crisp MCP on Cursor AI Code Editor MCP Client Crisp MCP on Claude Desktop App MCP Integration Crisp MCP on OpenAI Agents SDK MCP Compatible Crisp MCP on Visual Studio Code MCP Extension Client Crisp MCP on GitHub Copilot AI Agent MCP Integration Crisp MCP on Google Gemini AI MCP Integration Crisp MCP on Lovable AI Development MCP Client Crisp MCP on Mistral AI Agents MCP Compatible Crisp MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
OpenAI Agents SDK

Connect Crisp MCP to OpenAI Agents SDK

Create your Vinkius account to connect Crisp 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

Query Live Visitor & Chat Data

This MCP Server gives your agent direct access to your Crisp account. Use `list_conversations` to get a feed of ongoing chats or `get_messages` to read the history of a specific one. Your agent gets the context it needs before ever writing a response. Because you're using the OpenAI Agents SDK, every tool call is logged in your OpenAI tracing dashboard. You can see exactly which data your agent requested with `get_visitor_profile` and what it received. This isn't a black box—it's a debuggable, production-ready system for customer support.

Send Messages with Agentic Control

Let your agent talk directly to website visitors. The `send_message` tool posts a reply to any active conversation on your behalf. This is how you move from just analyzing data to actively participating in support tickets. Here's the critical part for production: the OpenAI SDK includes guardrails. Your agent doesn't just fire off messages. It proposes an action, and your code gets a final chance to approve or deny it. This built-in checkpoint prevents your agent from sending the wrong message to the wrong person, giving you the safety needed for a live environment.

Build Specialized Support Teams

Go beyond a single, monolithic agent. You can fetch a customer's details with `get_visitor_profile` to see who they are. Your agent can then use that information to make smarter decisions about how to handle the conversation. The SDK's architecture lets you hand off tasks between specialized agents. For instance, a triage agent can use `list_visitors` to check for a VIP tag. If it finds one, it can pass the entire conversation context to a high-priority agent for white-glove service. That's how you build a sophisticated, multi-agent system on top of Crisp.

Setup guide

Set up Crisp 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. 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. 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 Crisp tools at runtime.

  3. 3

    Create your Agent

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

  4. 4

    Run the agent

    Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Crisp 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="Crisp Agent",
            instructions="You have access to Crisp tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Crisp. 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.

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 Crisp MCP in OpenAI Agents SDK

Just install the SDK and point it to the Vinkius endpoint URL. Your agent will automatically discover all the Crisp tools like `send_message` and `list_conversations`. Set `cacheToolsList=True` in the server config for better performance.
Yes, but you handle this in your agent's logic. The MCP Server exposes all tools by default. Your code's guardrails are responsible for approving or denying calls to specific tools, giving you fine-grained control over agent actions.
Use the tracing dashboard provided by OpenAI. Every call your agent makes to the Crisp MCP Server, like `get_messages`, and the data it gets back, will be visible there. It’s the easiest way to see what your agent is thinking.
Yes. You add the Vinkius MCP Server to the agent's constructor. It doesn't replace your existing tools; it adds the set of Crisp tools to the agent's capabilities.
Your agent requests specific data, like conversation contents or visitor profiles, through the MCP Server. That data is passed from Crisp to your agent via Vinkius's ephemeral, zero-trust sandbox. Nothing is stored on our servers, but be aware that tool inputs and outputs may be visible in your OpenAI tracing logs per your data agreement with them.

Start using the Crisp MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 6 tools

We've already built the connector for Crisp. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 6 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.