How to Use the Crisp MCP in Google ADK

Q: How does the Google ADK find the tools for the Crisp MCP Server?

You instantiate an McpToolset with your Vinkius server URL and pass it to your LlmAgent. The ADK handles discovery, making all the Crisp tools available to your Gemini agent.

Q: Can I use this to analyze Crisp support trends with the Google ADK?

Absolutely. That's a core use case. Have your agent use listconversations and getmessages to fetch the data, then use native Google Cloud tools to push it into BigQuery for large-scale analysis.

Q: Can I choose which Crisp tools my Google ADK agent sees?

Yes. The McpToolset constructor in the Google ADK has a toolnames filter. You can provide a list of tool names, like sendmessage, to expose only a specific subset to your agent.

Connect Gemini agents to your Crisp data using the Google ADK. Pipe support conversations directly into BigQuery for analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crisp MCP to Google ADK

Create your Vinkius account to connect Crisp to Google ADK 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 Crisp with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull Crisp Data into Google Cloud

This server exposes your Crisp support data through a standard interface. Your agent can use `list_conversations` and `get_messages` to pull complete chat logs from your website. It's a direct pipeline from your front-line support into your cloud environment. Once the data is in, the real work begins. Since you're using the Google ADK, you can have your agent automatically stream these conversations into a BigQuery table. Now you can run large-scale analytics on support response times, common customer issues, and resolution rates across your entire history.

Reason Across Full Customer Histories

Give your agent a perfect memory. Use tools like `get_visitor_profile` and `get_messages` to pull a user's complete interaction history from Crisp. You aren't just getting the last five messages; you can get everything. This is where Gemini's long-context window shines. An agent can load a customer's entire support history—potentially thousands of messages—into a single prompt. It can then use `send_message` to provide a response that's aware of every past problem and solution, so customers never have to repeat themselves.

Your Crisp MCP Server on GCP

Treat Crisp as a native service in your Google Cloud ecosystem. Your agent can monitor for new support tickets with `list_conversations`. When a specific type of issue is detected, it can trigger other actions in your infrastructure. This MCP Server is the starting point for complex, enterprise workflows. An agent could identify a billing question in a Crisp chat, pull the user's account details with `get_visitor_profile`, and then trigger a Google Cloud Function to check their subscription status in your own database. It connects your customer-facing chat to your internal systems.

Setup guide

Set up Crisp MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Crisp tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Crisp_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Crisp tools via MCP.",
    tools=mcp_tools,
)

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 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.

Connect Crisp 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 Crisp MCP in Google ADK

You instantiate an `McpToolset` with your Vinkius server URL and pass it to your `LlmAgent`. The ADK handles discovery, making all the Crisp tools available to your Gemini agent.

Absolutely. That's a core use case. Have your agent use `list_conversations` and `get_messages` to fetch the data, then use native Google Cloud tools to push it into BigQuery for large-scale analysis.

Yes. The `McpToolset` constructor in the Google ADK has a `tool_names` filter. You can provide a list of tool names, like `send_message`, to expose only a specific subset to your agent.

No. Your agent running on Google Cloud makes a secure outbound HTTPS request to the Vinkius endpoint. There's no need for inbound firewall rules or public IPs, as Vinkius handles the connection to Crisp for you.

The MCP Server acts as a secure proxy. When your agent calls a tool, we fetch the requested data—like visitor profiles or message lists—from Crisp and stream it to your agent in your GCP environment. The data passes through our ephemeral instances and is subject to your own Google Cloud security policies once it arrives.

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