How do I find the project key I need to use with most tools?

Start by asking the agent to run `list_chattermill_projects`. This returns all your projects with their keys. Most Chattermill API endpoints — responses, themes, metrics, etc. — require this project key as the first parameter.

What customer experience metrics can I retrieve?

Use `get_chattermill_metric` with a metric type of `nps`, `average_score`, `net_sentiment`, or `volume`. You can filter by date range, category, or theme for more targeted insights. All metrics require a project key.

Where do I find my Chattermill API Key?

Log in to your Chattermill account and navigate to **Settings > API**. You can generate and copy your personal API Key from that section. The key is used as a Bearer token on every API request.

Chattermill MCP Server for Pydantic AI 11 tools — connect in under 2 minutes

Name: Chattermill
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 11 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Chattermill through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Chattermill "
            "(11 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Chattermill?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Chattermill MCP Server

Connect your Chattermill account to any AI agent and take full control of your customer experience (CX) intelligence through natural conversation. Unify feedback from Zendesk, App Store, Typeform, and dozens of other sources into one AI-powered view.

Pydantic AI validates every Chattermill tool response against typed schemas, catching data inconsistencies at build time. Connect 11 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Project Management — List and inspect all feedback projects configured in your account
Feedback Intelligence — Browse, filter, and paginate customer responses with full date and source filtering
Theme Analysis — Explore AI-generated themes and categories to pinpoint recurring customer issues
Metric Insights — Retrieve calculated NPS, CSAT, net sentiment, and volume metrics on demand
Source Auditing — List all data sources and data types feeding your feedback pipeline
Segmentation — Access custom segments for advanced cohort analysis
Data Ingestion — Submit new feedback entries for analysis directly from your agent

The Chattermill MCP Server exposes 11 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Chattermill to Pydantic AI via MCP

Follow these steps to integrate the Chattermill MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 11 tools from Chattermill with type-safe schemas

Why Use Pydantic AI with the Chattermill MCP Server

Pydantic AI provides unique advantages when paired with Chattermill through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Chattermill integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Chattermill connection logic from agent behavior for testable, maintainable code

Chattermill + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Chattermill MCP Server delivers measurable value.

Type-safe data pipelines: query Chattermill with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Chattermill tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Chattermill and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Chattermill responses and write comprehensive agent tests

Chattermill MCP Tools for Pydantic AI (11)

These 11 tools become available when you connect Chattermill to Pydantic AI via MCP:

get_chattermill_metric

Valid metric_type values: nps, average_score, net_sentiment, volume. Supports optional date range filtering with UNIX timestamps. Retrieve a calculated metric (NPS, CSAT, sentiment, volume) for a project

get_chattermill_project

Use list_chattermill_projects first if the project ID is unknown. Get details of a specific Chattermill project by its ID

get_response_details

Returns the comment, score, metadata, and applied themes. Get detailed information for a single feedback response

list_chattermill_projects

Use this first to obtain the project key needed by all other Chattermill tools. The project key is typically a lowercase version of the company name. List all available feedback projects in the Chattermill account

list_custom_segments

Returns user-defined segments used for advanced filtering and cohort analysis. List custom segments defined for a project

list_data_types

Returns data classification types used to categorize responses. Use this to discover type keys for filtering. List all feedback data types for a project (e.g. NPS, review, survey)

list_feedback_responses

Supports pagination via page/per_page and date filtering via date_from/date_to in YYYYMMDD_HHMMSS format. Default: page 1, 20 results per page, max 100. List paginated feedback responses for a specific project

list_feedback_sources

Returns configured data ingestion sources. Use this to discover available source keys for filtering responses. List all feedback data sources for a project (e.g. Zendesk, App Store, Typeform)

list_feedback_themes

Returns themes automatically generated by Chattermill ML to classify recurring customer topics. List AI-generated feedback themes detected in a project

list_theme_categories

Categories are parent groupings for themes, useful for high-level trend analysis. List categories that group feedback themes together

submit_feedback_response

Requires the project_key plus comment text. Optionally supply score, data_source, and data_type keys from their respective list endpoints. Submit a new feedback response to a Chattermill project

Example Prompts for Chattermill in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Chattermill immediately.

"List all my Chattermill projects and then show me the latest feedback responses from the first one."

"What is our current NPS score for the 'acme' project?"

"Show me the AI-detected themes and their categories for my mobile app project."

Troubleshooting Chattermill MCP Server with Pydantic AI

Common issues when connecting Chattermill to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Chattermill + Pydantic AI FAQ

Common questions about integrating Chattermill MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Chattermill MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.