Integration

Opinion Stage integration

Opinion Stage builds quizzes, surveys, assessments, calculators and forms; its Results API reads what those items collect. An agent can list the items of the account (type, title, status, embed code and links), read one item, list or read the responses an item received (each answer, the result shown, UTM source and duration), and list an item's questions with their kind (text, select or boolean). It is read-only, answers in JSON:API format, is marked beta by the vendor, and does not support the poll format. Authentication is the personal API key from the account page, sent in the Authorization header with the Apikey prefix.

Connect Opinion Stage How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Opinion Stage.Built from the 5 Opinion Stage tools below, on the connection you add once.

What you can do with Opinion Stage

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.

Item, 2 operations

get_itemGet itemGETReturns one item by id: its type, title, status (published, closed, deleted or draft), creation and modification times, embed script and iframe code, and its dashboard, landing page and questions links. An unknown id answers 404 not found.
list_itemsList itemsGETLists the account's items (trivia, personality, recommendation quizzes, assessments, calculators, surveys), a page at a time; meta.page.total is the page count. Each: id, type, title, status (published, closed, deleted, draft), times, embed, links.

Response, 2 operations

get_item_responseGet item responseGETReturns one response of an item by id: its creation time, the answers given per question (selected options, free text or a true/false value), the result (title and text), the UTM source and the time spent. An unknown id answers 404 not found.
list_item_responsesList item responsesGETLists an item's responses, one page at a time: id, creation time, answers per question (selected options, free text or true/false; pair question ids with list_item_questions for titles), result (title, text), UTM source, time spent.

Question, 1 operation

list_item_questionsList item questionsGETLists an item's questions, one page at a time: id (matches the question field of each answer in list_item_responses), title, kind (text, select or boolean), whether it belongs to the lead form, creation and modification times.

Use Opinion Stage from Claude Code, Cursor or Codex

Connect Opinion Stage in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Opinion Stage 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 Opinion Stage

Create your workspace
Sign up free. Nothing to install.
Connect Opinion Stage once
Add your Opinion Stage 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.