How to Use the Chattermill MCP in Claude Code

Q: How do I configure Chattermill with Claude Code?

Run the command claude mcp add --transport http chattermill-mcp -- in your terminal. This adds the MCP server to your /.claude.json configuration file, making all tools immediately available.

Q: Can I use Claude Code to submit feedback responses directly to Chattermill?

Yes, you can pipe local data into submitfeedbackresponse to send comments directly to your feedback project. This is useful for automating feedback ingestion from local logs or offline surveys.

Q: How do I find my Chattermill project key using Claude Code?

Run listchattermillprojects through the CLI to list all active feedback projects. The command will output the project keys, which you can then pass to other tools for filtering.

Q: Can I filter feedback by specific data sources?

Yes. You can run listfeedbacksources to get a list of active channels like Zendesk or App Store reviews, then filter your feedback queries using those specific source keys.

Pipe Chattermill metrics and customer feedback themes directly into your terminal scripts with Claude Code.

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 Claude Code

Create your Vinkius account to connect Chattermill to Claude Code 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 Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate sentiment reports via Claude Code

`get_chattermill_metric` extracts NPS, CSAT, or net sentiment scores directly into your terminal. This MCP server extracts these numbers so you can write bash scripts that alert your team when user sentiment drops below a specific threshold. Claude Code runs the query, formats the output, and lets you pipe the results to other command-line utilities. It is built for developers who want to monitor customer satisfaction without leaving their shell.

Query raw feedback via the command line

`list_feedback_responses` retrieves customer feedback entries using terminal-friendly pagination and date filters. You can search for specific keywords or filter by date ranges using UNIX timestamps. This tool allows you to grep through customer comments directly from your command line. Claude Code handles the API requests and formats the JSON output so you can quickly analyze recent bugs or feature requests.

Track automated classification themes

`list_feedback_themes` exposes the machine learning themes detected in your customer comments. Claude Code uses these themes to compile quick reports via the MCP connection directly inside your terminal session. You can combine this with `list_theme_categories` to see high-level trends. It gives you a fast way to check if a recent deployment caused a spike in UI or performance complaints without opening a browser.

Setup guide

Set up Chattermill MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see chattermill-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Chattermill transactions." It will automatically discover and invoke the available Chattermill tools.

Terminal

claude mcp add --transport http chattermill-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Chattermill MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "chattermill-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Code

Run the command `claude mcp add --transport http chattermill-mcp -- ` in your terminal. This adds the MCP server to your `~/.claude.json` configuration file, making all tools immediately available.

Yes, you can pipe local data into `submit_feedback_response` to send comments directly to your feedback project. This is useful for automating feedback ingestion from local logs or offline surveys.

Run `list_chattermill_projects` through the CLI to list all active feedback projects. The command will output the project keys, which you can then pass to other tools for filtering.

Yes. You can run `list_feedback_sources` to get a list of active channels like Zendesk or App Store reviews, then filter your feedback queries using those specific source keys.

Vinkius uses zero-trust network isolation to ensure that your feedback themes and project keys are never exposed. All communication between Claude Code and the API is encrypted, and credentials are kept secure inside your local configuration.

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