How to Use the Chattermill MCP in Pydantic AI

Q: How do I configure Chattermill with Pydantic AI?

Install pydantic-ai-slimmcp. Use the MCPToolset class with your HTTP endpoint URL and pass it into the toolsets array when building your Agent.

Q: How do I find specific customer segments in Chattermill?

The agent runs listcustomsegments. It returns the exact user-defined cohorts available for that project, which you can then use for advanced filtering.

Build strictly typed, fail-safe agents that query Chattermill data with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Chattermill to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict types on Pydantic AI feedback queries

Silent failures ruin data pipelines. When your agent calls `get_chattermill_metric`, the framework validates the returned NPS or average score against your predefined models. If the API returns a string instead of a float, the system fails loudly rather than corrupting your downstream reports. Pagination parameters get the same strict treatment. The agent queries `list_feedback_responses` using exact YYYYMMDD_HHMMSS date strings. You never have to worry about hallucinated timestamps breaking the API call because the runtime validation catches it first.

Discover project structures via the MCP Server

Hardcoding IDs leads to brittle code. The agent fetches the active project key by executing `list_chattermill_projects` and validates the lowercase string format instantly. It uses that key to pull detailed configurations via `list_feedback_sources` and `list_data_types`. Cohort analysis requires exact segment names. Running `list_custom_segments` ensures your agent only filters data using segments that actually exist in the account. When it needs granular data, it passes validated IDs to `get_response_details` to extract the raw comment and score.

Validate theme mappings automatically

Machine learning tags change frequently. The agent calls `list_feedback_themes` to pull the latest AI-generated topics from the platform. It maps these specific topics to their parent groups by hitting `list_theme_categories`. Pushing new feedback demands correct metadata. The agent triggers `submit_feedback_response` only after confirming the data source and type match the platform's requirements. Every payload is type-checked before leaving your local environment.

Setup guide

Set up Chattermill MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "chattermill-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Chattermill tools.",
)

result = await agent.run("List recent Chattermill transactions")
print(result.output)

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 Pydantic AI

Install pydantic-ai-slim[mcp]. Use the MCPToolset class with your HTTP endpoint URL and pass it into the toolsets array when building your Agent.

Yes. The framework ensures the agent only requests allowed metric types like nps, average_score, or volume from `get_chattermill_metric`. Anything else triggers an immediate validation error.

It works with any model you choose. Since the framework is model-agnostic, you can route feedback responses through OpenAI, Anthropic, or a local instance without changing the MCP Server setup.

The agent runs `list_custom_segments`. It returns the exact user-defined cohorts available for that project, which you can then use for advanced filtering.

Your raw customer comments and applied ML themes remain entirely secure. Vinkius manages the authentication externally and runs the MCP Server in an ephemeral sandbox. Your agent accesses the data without ever exposing credentials to the LLM provider.

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