surveyloop

surveyloop

surveyloop is a small local bridge to the hosted Inquira MCP server, which runs AI surveys end to end. Describe a research goal and it generates a professional survey for it; from there you can publish the survey, share its link, read the responses that come back, and ask for an AI analysis report with an executive summary, key metrics, per-question insights and action recommendations.

The bridge keeps no survey data of its own. It serves the upstream server's tool list locally, exactly as captured from the live endpoint, and forwards each tool call upstream, returning the result untouched. The captured surface stops at returning a survey's own share link: sending that link to anyone is the caller's own act, and there is no outreach or sending tool in it.

Tools

• create_survey — generate a survey from a research goal. Required: goal. Optional: lang (one of "en", "zh", "ja", "es", "pt"; defaults to "en") and publish (publish immediately after creation; defaults to false). Returns the survey ID and shareable link.
• get_surveys — list all surveys belonging to the authenticated user. Optional: status (one of "all", "published", "draft"; defaults to "all").
• get_responses — get all responses submitted to a specific survey. Required: survey_id.
• get_ai_report — generate an AI analysis report for a survey's responses. Required: survey_id.
• publish_survey — publish a survey to make it accessible via its share link. Required: survey_id.
• get_survey_link — get the shareable link for a published survey. Required: survey_id.

Configuration

• INQUIRA_MCP_URL (optional) — override the upstream endpoint. Defaults to https://getinquira.com/api/mcp. (The override hook is this rebuild's own labelled reconstruction.)
• INQUIRA_API_KEY (optional) — when set, every upstream request carries an Authorization: Bearer <key> header, for the caller's own Inquira key. When it is not set, no key header is sent. (The header name is pinned by the original's registry record; the Bearer scheme and this env forwarding are labelled reconstructions — the original surface was captured keyless.)

Forwarding mechanics

On the first tool call the client opens a streamable HTTP session with the upstream: a JSON-RPC initialize request (protocolVersion 2025-03-26, clientInfo name surveyloop), then a notifications/initialized notification, then the tools/call request carrying the caller's arguments unchanged. When the upstream answers initialize with an Mcp-Session-Id header, that value rides on every later request of the session, which is reused for the life of the process. Replies may arrive as plain JSON or as server-sent events; both are read.

Successful upstream results pass through verbatim, including any isError flag the upstream sets. Failures — a JSON-RPC error, a non-2xx status, an unreadable response, or a request that cannot be completed — come back as an isError result whose text starts with surveyloop error: (this rendering is this rebuild's own labelled reconstruction).

CLI

Each tool is also a subcommand taking one JSON argument string:

npx @reneturcios/surveyloop create_survey '{"goal":"Customer satisfaction survey for our SaaS product after onboarding","lang":"en"}'
npx @reneturcios/surveyloop get_responses '{"survey_id":"sv_123"}'
npx @reneturcios/surveyloop --version

Exit codes: 0 on success, 1 on an isError result, 2 on a usage error.

MCP server

npx -y @reneturcios/surveyloop mcp

MCP client config:

{
  "mcpServers": {
    "surveyloop": {
      "command": "npx",
      "args": ["-y", "@reneturcios/surveyloop", "mcp"]
    }
  }
}

Docker

docker run -i ghcr.io/cloudcorprecords/surveyloop
docker run --rm ghcr.io/cloudcorprecords/surveyloop --version

The container's default command is mcp, so the first form is a stdio MCP server; any other arguments reach the CLI normally.

Development

npm install
npm run build
npm test
npm run dev

The test suite runs entirely against a stubbed JSON-RPC upstream — no live network calls.

License

MIT — see LICENSE.