MCP App Store
by KeenEthics
Iterate icon

Iterate MCP Server for Claude and ChatGPT

By Iterate

Overview

Connect Iterate to Claude to build surveys and understand what your customers are telling you. Explore existing surveys and their questions, search customer responses, retrieve submitted images, and compare themes, sentiment, response volume, NPS, CSAT, and ratings across surveys or time periods. Work with Claude to turn your research goals into unpublished survey drafts, including ranking, MaxDiff, and conjoint questions. Refine existing surveys by adding, editing, removing, or reordering questions, configuring branching logic, and adjusting supported question settings. Requires an Iterate administrator account and appropriate project permissions. Survey creation and editing require write access, with changes reviewed and confirmed in conversation. Existing live surveys can be edited. The connector does not publish surveys, select recipients, send campaigns, or modify stored responses. Results may include connected account details, original answers, and submitted images.

How to connect

  1. Claude: Open the Iterate listing in the Claude connectors directory and choose Connect. Claude listing Iterate exposes 14 tools here.
  2. ChatGPT: Open the Iterate listing in the ChatGPT app directory and choose Connect. ChatGPT listing Iterate exposes 15 tools here.

Tools

add_survey_question

ChatGPT
Read get_survey_questions first, present the proposed changes, and obtain explicit confirmation before writing. Explain the effect on surveys already in use. One confirmation can cover multiple editing calls. Requires surveys:create and administrator access to a writable project. Only flat surveys with freeform, single choice, multiple choice, rating, NPS, and CSAT questions are supported. Live surveys can be edited without pausing collection. Never changes delivery, targeting, or publication settings. After an error or uncertain result, reread the survey before retrying. Adds one new question using the create_survey question schema. Omit before_question_id to append. Adding is not idempotent: check the saved question IDs before retrying an uncertain call.

aggregate_feedback

ChatGPT
Returns aggregate metrics over feedback (server-side counts, never raw responses) so you can answer questions like top themes, sentiment split, and which survey is most negative without reading rows. All inputs optional: survey_id (omit to span every survey), question_id, since/until (RFC3339), group_by (none, survey, week, month), metrics (any of volume, sentiment, topics, scores; defaults to volume, sentiment, topics), top_n (topics per group, default 10). Use list_surveys to get a survey_id; use get_responses only when you need the actual text.

create_survey

ChatGPT
Creates one safe, non-live survey draft after the customer has explicitly confirmed the complete proposal. Before calling: ask what the customer is trying to learn, ask only essential audience and delivery follow-ups, use get_survey_creation_context, propose the 3–5 best questions, and show the full survey, including advanced options, for confirmation. When an existing survey appears relevant, use list_surveys and get_survey_questions to understand the account's terminology and avoid duplication; do not copy it verbatim. Supported question types are freeform, single_choice, multiple_choice, rating, nps, and csat. Questions should be neutral, focused on one idea each, varied when useful, and include an open-ended question when it will add insight. All questions default to optional and may have a subheader or be required. Choice questions support Other with a custom label and randomization; multiple choice supports selection limits; freeform supports a character limit. Connected integration delivery methods may be selected when returned by get_survey_creation_context, but targeting, recipients, and campaign configuration happen later in Iterate. This tool never sends email, contacts respondents, displays a survey, or publishes an integration campaign. Call it once after confirmation; if the outcome is unclear, use list_surveys to check before trying again. If validation requires a material revision, show the revised draft and obtain confirmation again before retrying.

download_response_image

ChatGPT
Returns a temporary download link for an image submitted to a file upload question. Pass the survey_id and response_id returned by get_responses or search_responses. The link expires after 15 minutes.

get_responses

ChatGPT
Returns recent feedback responses for one survey (newest first), each with its question, answer, sentiment, and topics. Get a survey_id from list_surveys. Use limit (default 25, max 100), since (RFC3339), and cursor (next_cursor from a prior call) to page.

get_survey_creation_context

ChatGPT
Returns the writable projects and the eligible and unavailable delivery methods for the connected Iterate account, including email and in-app variants for connected integrations. Call this before proposing a survey draft. Ask what the customer is trying to learn first, ask only essential follow-up questions, and normally propose 3–5 varied, neutral questions. Targeting, recipients, and external campaign configuration happen later in Iterate.

get_survey_questions

ChatGPT
Returns a survey's name, delivery and state flags, and ordered top-level question IDs, types, respondent-facing prompts, choices with stored values, and supported question settings. Get a survey_id from list_surveys. State flags do not prove a survey has been shared or delivered. Use this to review a created draft or understand an existing survey's terminology and avoid duplicating questions; do not copy it verbatim.

list_surveys

ChatGPT
Lists the surveys on the authenticated user's Iterate account, each with its id, name, type, platform, creation date, and total response count. Pass a survey's id to get_survey_questions to read its questions or get_responses to read its feedback.

preview_survey

ChatGPT
Shows an interactive preview of an unsaved survey using all question types and options accepted by create_survey, with 1–20 top-level questions. First use get_survey_creation_context to confirm a writable project and the intended survey delivery type, such as link, email, website, mobile, or an eligible integration. Ask how the survey will be delivered if that is not already clear; do not guess. The preview inherits the selected project's default colour. For a revision, call again with the complete revised proposal, project_id, and delivery_key; answers and progress reset. Branching and follow-up questions are configured later in Iterate. File upload is displayed without uploading files. Preview answers are discarded and never become feedback. Save draft requests saving the exact proposal, project, and delivery type through the conversation using create_survey. It does not itself create a survey. Save once, and keep targeting, recipients, campaign configuration, and publishing in Iterate; return the saved draft's dashboard_url.

remove_survey_question

ChatGPT
Read get_survey_questions first, present the proposed changes, and obtain explicit confirmation before writing. Explain the effect on surveys already in use. One confirmation can cover multiple editing calls. Requires surveys:create and administrator access to a writable project. Only flat surveys with freeform, single choice, multiple choice, rating, NPS, and CSAT questions are supported. Live surveys can be edited without pausing collection. Never changes delivery, targeting, or publication settings. After an error or uncertain result, reread the survey before retrying. Detaches a question from the survey while retaining its document and historical responses. It will no longer be shown to respondents. Cannot remove the final question.

reorder_survey_questions

ChatGPT
Read get_survey_questions first, present the proposed changes, and obtain explicit confirmation before writing. Explain the effect on surveys already in use. One confirmation can cover multiple editing calls. Requires surveys:create and administrator access to a writable project. Only flat surveys with freeform, single choice, multiple choice, rating, NPS, and CSAT questions are supported. Live surveys can be edited without pausing collection. Never changes delivery, targeting, or publication settings. After an error or uncertain result, reread the survey before retrying. Reorders questions using the complete list of current question_ids, each exactly once. This changes respondent order without changing the questions or their stored answers.

search_responses

ChatGPT
Searches feedback responses across surveys (newest first) and returns matching quotes, each with its survey, question, answer, sentiment, and topics. Use it to answer things like what customers are saying about a keyword across every survey. All inputs optional: query (free-text match on the response), survey_id (omit to search all surveys), sentiment (positive/neutral/negative), topic (exact match), since/until (RFC3339), limit (default 25, max 100), cursor (next_cursor from a prior call). For every response in one survey in order, use get_responses instead.

update_survey_question

ChatGPT
Read get_survey_questions first, present the proposed changes, and obtain explicit confirmation before writing. Explain the effect on surveys already in use. One confirmation can cover multiple editing calls. Requires surveys:create and administrator access to a writable project. Only flat surveys with freeform, single choice, multiple choice, rating, NPS, and CSAT questions are supported. Live surveys can be edited without pausing collection. Never changes delivery, targeting, or publication settings. After an error or uncertain result, reread the survey before retrying. Updates only the fields in patch. Omitted fields stay unchanged; false disables a setting; null clears nullable settings. Question type and rating scale size cannot change. Retain existing choice values when renaming or reordering choices. Historical answers remain stored; changing labels changes how those answers are described in reports.

update_survey_rating_direction

ChatGPT
Read get_survey_questions first, present the proposed changes, and obtain explicit confirmation before writing. Explain the effect on surveys already in use. One confirmation can cover multiple editing calls. Requires surveys:create and administrator access to a writable project. Only surveys without branches and with freeform, single choice, multiple choice, rating, NPS, CSAT, statement, number, emoji, user info, file upload, date, ranking, matrix, and legal questions are supported; a legal question may keep its default branch, where disagreeing ends the survey. Live surveys can be edited without pausing collection. Never changes delivery, targeting, or publication settings. After an error or uncertain result, reread the survey before retrying. Changes only consistent_rating_direction for the whole survey. When true, each respondent sees one consistent direction across all non-star rating questions, overriding their individual answer order. When false, individual question settings apply again; variable questions choose their direction independently. Explain this survey-wide effect before confirmation. Individual settings and existing responses stay stored.

update_survey_settings

ChatGPT
Read get_survey_questions first, present the proposed changes, and obtain explicit confirmation before writing. Explain the effect on surveys already in use. One confirmation can cover multiple editing calls. Requires surveys:create and administrator access to a writable project. Unsupported question types and branches do not block unrelated edits; each tool describes its own restrictions. When translation_languages is present, warn before wording changes that translated respondents may still see the old wording. Leave translations unchanged and direct the user to the Dashboard to review or add updated translations if they proceed. Live surveys can be edited without pausing collection. Never changes delivery, targeting, or publication settings. After an error or uncertain result, reread the survey before retrying. Changes only the survey-wide settings supplied in settings; omitted settings stay unchanged. Question settings are changed with update_survey_question. consistent_rating_direction overrides individual rating question answer order; explain this survey-wide effect before confirmation. Individual settings and existing responses stay stored.

whoami

ChatGPT
Returns the authenticated Iterate user's email and company name. Use it to confirm which account is connected.

add_survey_question

Claude

aggregate_feedback

Claude

create_survey

Claude

download_response_image

Claude

get_responses

Claude

get_survey_creation_context

Claude

get_survey_questions

Claude

list_surveys

Claude

remove_survey_question

Claude

reorder_survey_questions

Claude

search_responses

Claude

update_survey_question

Claude

update_survey_settings

Claude

whoami

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/iterate"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/iterate)