How to Use the Chattermill MCP in Google ADK

Q: Can I filter the Chattermill tools exposed to my Google ADK agent?

Yes. You can pass a toolnames list to restrict the agent. This prevents it from accidentally calling submission endpoints if you only want it reading metrics.

Q: How does the agent filter responses by date in Chattermill?

It passes specific datefrom and dateto parameters to listfeedbackresponses. The format requires YYYYMMDDHHMMSS strings, which Gemini formats correctly on its own.

Q: What happens if the agent does not know the Chattermill project ID?

The agent will call getchattermillproject or listchattermillprojects first. It retrieves the correct ID and uses it for all subsequent metric or response queries.

Feed massive batches of Chattermill customer feedback into Gemini using the Google ADK.

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 Google ADK

Create your Vinkius account to connect Chattermill 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 Chattermill with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pipe feedback directly into Google ADK pipelines

Gemini's massive context window changes how you handle support data. Your agent pulls hundreds of records using `list_feedback_responses` and feeds them straight into the model. It cross-references those comments with available ingestion endpoints discovered via `list_feedback_sources`. You skip the manual ETL steps. The agent queries `get_chattermill_metric` to grab raw NPS and volume stats over specific UNIX timestamp ranges. It then analyzes that data alongside your existing BigQuery tables for deep enterprise insights.

Map AI themes across massive datasets

Unstructured text needs structure before it hits your database. The agent runs `list_feedback_themes` to find out exactly how Chattermill classified recent complaints. It groups those insights by hitting `list_theme_categories` for high-level trend reporting. Filtering by specific user cohorts is built right in. Call `list_custom_segments` to isolate feedback from enterprise tier customers. The agent then inspects the worst-performing interactions using `get_response_details` to extract the exact scores and metadata.

Write support metrics back via the MCP Server

Agents don't just read data here. They push new records back into the system by calling `submit_feedback_response` with the required project key and comment text. You can map custom inputs from Vertex AI directly into the feedback loop. Figuring out the right tags happens on the fly. The agent checks `list_data_types` to tag the incoming text as a review or survey. It finds the correct project destination by running `list_chattermill_projects` before submitting the payload.

Setup guide

Set up Chattermill 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 Chattermill 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="Chattermill_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Chattermill 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 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 Google ADK

Install google-adk via pip. Create an McpToolset using StreamableHttpServerParameters with your Vinkius URL, then pass that toolset directly to your LlmAgent instance.

Yes. You can pass a tool_names list to restrict the agent. This prevents it from accidentally calling submission endpoints if you only want it reading metrics.

It passes specific date_from and date_to parameters to `list_feedback_responses`. The format requires YYYYMMDD_HHMMSS strings, which Gemini formats correctly on its own.

The agent will call `get_chattermill_project` or `list_chattermill_projects` first. It retrieves the correct ID and uses it for all subsequent metric or response queries.

Your raw survey responses and net sentiment scores are fully isolated. Vinkius relies on a zero-trust architecture that requires a single endpoint token. The MCP connection is ephemeral and drops the moment the task finishes.

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