Integration

Chattermill integration

Chattermill analyzes customer feedback (surveys, reviews, support conversations) and tags it with themes and sentiment. List the projects of the account; list a project's responses with filters on dates, score, data type, data source, segment, theme and processing state, read one response with its detected themes, phrases and sentiment, add new feedback, update a response's metadata and segments, delete a response for a data erasure request, and list the project's data types and data sources. Not exposed: searching responses by attribute (the encoding of its filter keys is not documented), and themes, categories, attributes, tags, custom segments and metrics (their answers are not documented). Authentication is the API key from Chattermill's API settings page, sent as a Bearer token.

Connect Chattermill How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Chattermill.Built from the 9 Chattermill tools below, on the connection you add once.

What you can do with Chattermill

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Response, 5 operations

create_responseCreate responsePOSTAdds a response (a piece of customer feedback) to a project: comment, score, metadata (user_meta), segments, data type and data source. Chattermill then processes it for themes and sentiment.
delete_responseDelete responseDELETEPermanently deletes a response, for example to honor a data erasure (GDPR) request. This cannot be undone.
get_responseGet responseGETReturns one response (customer feedback): score, original and processed comment, metadata attributes, detected themes and phrases with their sentiment. Personal data.
list_responsesList responsesGETLists a project's responses (customer feedback), 20 per page by default and 100 at most: score, comment, metadata attributes, detected themes, phrases and sentiment. Filter by dates, score, data type or source, segment or theme. Personal data.
update_responseUpdate responsePUTAdds or changes the metadata (user_meta) and segments of an existing response, for example to enrich feedback with data from your CRM.

Project, 2 operations

get_projectGet projectGETReturns one Chattermill project by its numeric id: its key (used by the other tools) and name.
list_projectsList projectsGETLists the Chattermill projects the API key can access, with each project's numeric id, key and name. The key is the project parameter of every other tool.

Data source, 1 operation

list_data_sourcesList data sourcesGETLists the data sources of a project (for example Zendesk or Typeform), where its responses come from; use their values to filter or create responses.

Data type, 1 operation

list_data_typesList data typesGETLists the data types of a project (for example nps or review), the dataset kinds responses are grouped by; use their values to filter or create responses.

Use Chattermill from Claude Code, Cursor or Codex

Connect Chattermill in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Chattermill operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Chattermill

Create your workspace
Sign up free. Nothing to install.
Connect Chattermill once
Add your Chattermill connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.