User Intuition

Name: User Intuition
Author: userintuition

Run end-to-end AI-moderated research with User Intuition.

От сообществаРаботаетБез входаГлобальныйБесплатноМожет изменять данные

Что умеет

List Studies: List studies. Rows are lightweight; use get_study for the full study plan, screeners, and targeting.
Create Study: Create an in-depth-interview, concept-test, or prototype-test draft using ordinary metadata only. Ask the human to explicitly choose recruiting_method (panel or BYOP). A value proposed o
Customize Study: Send one natural-language turn to the same stateful Customize Plan chat used by the dashboard. Use it for the research plan, audience or qualification criteria, screener questions, co

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Run end-to-end AI-moderated research with User Intuition. The hosted Streamable HTTP MCP exposes the full 33-tool research surface over OAuth: create and customize studies, configure panel or bring-your-own participants, launch voice, chat, or video interviews, manage participants and interviews, and generate evidence-backed reports. Supports concept and prototype tests, native concept images, and concept links. Connect at https://mcp.userintuition.ai/mcp.

Список инструментов сервера (33)

Технические названия из tools/list. Нужны только разработчикам.

list_studies	List studies. Rows are lightweight; use get_study for the full study plan, screeners, and targeting.
create_study	Create an in-depth-interview, concept-test, or prototype-test draft using ordinary metadata only. Ask the human to explicitly choose recruiting_method (panel or BYOP). A value proposed or inserted by a host/delegating model is not human confirmation unless it quotes the human's actual choice. Unless the human requests otherwise, use a voice interview in English with Elliot; these defaults are applied when interview_format, language, or voice are omitted. A prototype-test must use video or voice, never chat. Do not draft or pass the study plan, audience targeting, screener questions, concept links, or concept images here; after creation, send the user's natural-language research brief to customize_study. For a concept test, pass an accessible attachment through customize_study.concept_image or include a publicly downloadable concept-image URL in the message, plus its participant-facing label, stimulus context, audience, and learning goals. For a prototype test, include the prototype URL, participant-facing label, intended tasks, audience, and learning goals. The Customize Plan backend validates and attaches the asset. Voice applies only to voice/video, never chat.
customize_study	Send one natural-language turn to the same stateful Customize Plan chat used by the dashboard. Use it for the research plan, audience or qualification criteria, screener questions, concept links, and concept images. Pass the user's own description or answer without translating it into MCP-side schemas. If the client exposes an attached image as bytes or a readable local path, ask for a participant-facing label when missing, base64-encode the raw bytes, and send concept_image in this call; a public URL is not required. If response_type is question, relay the question to the user and call customize_study again with their answer. Completed plans and setting changes are persisted by the backend. After completion, call get_study and return its complete persisted study_plan for the user to review. If they request changes, continue this loop and return the revised plan. Once provisioning_status is provisioned, also share both dashboard_url and study_link without waiting for the user to ask.
get_study	Get the full persisted study, including the plan, audience targeting, screeners, and concept assets managed by customize_study. Call before metadata updates and after customization to verify the result. After customization, return the complete persisted study_plan to the user in a readable form and obtain explicit approval of the current plan before paid Panel launch or BYOP participant creation. When provisioning_status is provisioned, include both returned links in the completion response. dashboard_url is the researcher management link. study_link is the live participant interview link, not a test or preview link; opening it starts the participant experience. The public API does not expose a separate researcher-preview URL.
update_study	PATCH ordinary study metadata only. Use customize_study—not this tool—for the research plan, audience targeting, screener questions, concept links, or concept images. Only supplied fields change. Active panel studies must be paused or stopped first. Call get_study first.
delete_study	Delete a study.
pause_study	Pause a study while preserving its panel survey, target cycle, progress, and reward hold.
resume_study	Resume a paused study and continue its preserved panel recruitment.
stop_study	Stop panel recruitment, close the target cycle, and settle/release the active reward hold.
launch_panel	Launch paid recruitment for an existing Panel study. Before a paid launch, call get_study, return the complete current study_plan to the user, and obtain their explicit approval of both that plan and the dry-run cost/timeline estimate. country_code is always required and must support the study language. A launch fields exactly one country; when a brief names multiple countries, ask the human to select one launch country or create separately approved country-specific studies/launches. Show the resolved country and language from the dry-run response with the estimate. Use dry_run for the estimate; below 10% incidence use a feasibility request.
generate_report	Analyze the study interviews and return a fresh report.
get_study_report	Get the latest report, citations, interview count, and stale status.
list_participants	List BYOP participants. Panel respondents are anonymous interviews, not participant records.
create_participants	Create 1–100 unique BYOP participants for one study. Before creating participants, call get_study, return the complete current study_plan to the user, and obtain their explicit approval of that plan. Invitations send unless silent is true.
get_participant	Get one BYOP participant.
update_participant	Replace the mutable participant fields. Call get_participant first.
send_participant_reward	Send the configured incentive to a BYOP participant. The backend prevents duplicate rewards for an already-paid participant.
list_interviews	List lightweight interview rows. Fetch an interview to get messages, recordings, and screener responses.
get_interview	Get a full interview including messages, recording links, and screener responses.
delete_interview	Soft-delete an interview owned by the authenticated user.
list_panel_countries	List supported panel countries and language options. Filter by language OR country, never both.
submit_feasibility_request	Submit a low-incidence or specialized audience for manual feasibility review.
list_feasibility_requests	List the account feasibility requests, newest first.
get_feasibility_request	Get one feasibility request and its status or estimate.
create_webhook	Create an account-wide completed-interview webhook. The signing secret is shown once; store it securely.
delete_webhook	Delete an account webhook by URL.
list_available_languages	Return the supported interview languages as [{code, name, native_name}]. Call this before setting the public `language` field on create_study or update_study — only codes from this catalog are accepted.
list_available_modes	Return the supported interview modes (voice, chat, video). Pass the selected value as the public `interview_format` field on create_study or update_study.
list_study_types	Return the catalog of available study-type templates so the user or host model can select the metadata template before create_study. The Customize Plan backend—not the MCP host—loads and applies the selected row's planning instructions. Return the catalog of available study TYPES (e.g. "Win/Loss Analysis", "Churn Analysis", "NPS and CSAT", "Customer Onboarding", "Brand Health", "Market Intelligence", "Custom Design"). The response also includes a `recommended_slug` hinting at the best default for the current user based on their registration source. LIGHTWEIGHT response — heavy prompt fields (`chat_prompt`, `prompt`, and the voice-interviewer prompt) are stripped here to keep the catalog under MCP-client size caps. Each row returns {id, slug, title, description, recommended_slug, ...}. After picking a row, call `get_study_type(slug)` to load that row's full prompts. Use the public slug accepted by create_study; never pass the internal catalog id, system_prompt, or internal study_type classifier to a public tool.
get_study_type	Fetch one study-type row by slug, id, or exact title, including its prompt fields for inspection. Do not use those prompts to draft the plan in the MCP host; customize_study loads and applies the selected type's instructions server-side. `list_study_types` strips these heavy fields to fit MCP-client size caps. Lookup is exact-match (case-insensitive). If no row matches, you will get an error result.
get_interview_usage_stats	Aggregate call counts and durations over a date range. Use for "how many interviews did I run last month" / billing-style questions.
get_interviews_grouped_by_participants	Return calls grouped by their participant (invite). Useful when the user wants a per-participant view across studies.
list_voices	Return the catalog of available interviewer voices (id, name, provider, gender, accent). The public study tools currently accept the simplified `voice` values male or female; use this catalog for discovery and for legacy workflows that accept a provider voice id. Do not pass an internal voice_config object to public study tools.