humansurvey-mcp
HumanSurvey
웹사이트: humansurvey.co · 문서: humansurvey.co/docs · FAQ: humansurvey.co/faq
AI 에이전트를 위한 피드백 수집 인프라입니다.
HumanSurvey를 사용하면 장기적인 작업을 수행하는 에이전트가 여러 사람으로부터 구조화된 피드백을 수집할 수 있습니다:
Agent is doing a job
→ needs structured feedback from a group
→ creates survey from JSON schema
→ shares /s/{id} URL with respondents
→ humans respond over hours or days
→ agent retrieves structured JSON results and acts on them이것은 무엇인가요?
HumanSurvey는 단 하나의 좁은 작업을 위한 최소한의 API이자 MCP 서버입니다. 에이전트가 인간 그룹으로부터 구조화된 피드백을 수집하고 기계가 사용할 수 있는 결과를 다시 가져올 수 있도록 합니다.
다음과 같은 용도로 설계되었습니다:
설문조사가 필요한 이벤트 관리, 제품 출시 또는 커뮤니티 워크플로우를 실행하는 AI 에이전트
가벼운 피드백 수집 기본 요소가 필요한 에이전트 제품을 구축하는 개발자
다음과 같은 용도로는 설계되지 않았습니다:
설문조사 대시보드
시각적 양식 빌더
템플릿 라이브러리
이메일 캠페인
분석/보고 UI
Related MCP server: Datapoint MCP
주요 기능
JSON 스키마 입력 — 구조화되고 정밀하며 기계가 직접 생성 가능
MCP 서버 — Claude Code에서 직접 설문조사를 생성하고 결과를 읽음
최소한의 API 표면 — 인증된 생성자 경로, 공개 응답자 제출
4가지 의미론적 질문 유형 —
choice,text,scale,matrix조건부 로직 — Markdown 및 JSON 스키마의
showIf지원명시적 수명 주기 — 설문조사 종료, 만료 및 최대 응답 제한
제품 원칙
시각적 요소보다 의미론적 요소 우선: HumanSurvey는 UI 전용 필드 유형의 집합이 아닌 작은 프로토콜을 가집니다.
AI 우선 I/O: 에이전트가 설문조사를 작성하고 에이전트가 결과를 소비하며, 인간은 그 중간에 위치합니다.
모든 것은 API: 생성자 기능은 인증된 HTTP 및 MCP를 통해 사용할 수 있어야 합니다.
좁은 범위가 승리한다: 주로 인간 설문조사 운영자를 위한 기능이라면, 아마도 여기에 포함되지 않을 것입니다.
지원되는 질문 유형
single_choicemulti_choicetextscalematrix
Markdown 구문
# Survey Title
**Description:** Instructions for the respondent.
## Section Name
**Q1. Your question here?**
- ☐ Option A
- ☐ Option B
- ☐ Option C
**Q2. Multi-select question?** (select all that apply)
- ☐ Choice 1
- ☐ Choice 2
- ☐ Choice 3
**Q3. Open-ended question:**
> _______________
| # | Item | Rating |
|---|------|--------|
| 1 | Item A | ☐Good ☐OK ☐Bad |
| 2 | Item B | ☐Good ☐OK ☐Bad |척도(Scale) 질문:
**Q4. How severe is this issue?**
[scale 1-5 min-label="Low" max-label="Critical"]조건부 로직:
**Q1. Did the deploy fail?**
- ☐ Yes
- ☐ No
**Q2. Which step failed?**
> show if: Q1 = "Yes"
> _______________________________________________빠른 시작
Claude Code와 함께 사용하기
Claude Code 설정(~/.claude.json)에 추가하세요:
{
"mcpServers": {
"survey": {
"command": "npx",
"args": ["-y", "humansurvey-mcp"],
"env": {
"HUMANSURVEY_API_KEY": "hs_sk_your_key_here"
}
}
}
}그런 다음 Claude Code에서:
> Create a post-event feedback survey with a 1-5 rating, open text, and a yes/no question사용 가능한 도구:
create_key— API 키 자체 프로비저닝; 인간 설정 불필요create_survey— JSON 스키마에서 생성; 선택적max_responses,expires_at,webhook_urlget_results— 집계된 결과 + 원시 응답list_surveys— 키가 소유한 설문조사 목록close_survey— 설문조사를 즉시 종료
HTTP API 사용하기
curl -X POST https://www.humansurvey.co/api/keys \
-H "Content-Type: application/json" \
-d '{
"name": "my claude agent",
"email": "you@example.com",
"wallet_address": "eip155:8453:0xabc..."
}'모든 필드는 선택 사항입니다. wallet_address는 CAIP-10 형식을 사용하며, 향후 에이전트 네이티브 결제에 사용될 예정입니다.
그런 다음 설문조사를 생성하세요:
curl -X POST https://www.humansurvey.co/api/surveys \
-H "Authorization: Bearer hs_sk_..." \
-H "Content-Type: application/json" \
-d '{
"schema": {
"title": "Post-Event Feedback",
"sections": [{
"questions": [
{ "type": "scale", "label": "How would you rate the event?", "min": 1, "max": 5 },
{ "type": "text", "label": "What should we improve?" }
]
}]
}
}'응답:
{
"survey_url": "/s/abc123",
"question_count": 1
}결과 읽기:
curl https://www.humansurvey.co/api/surveys/abc123/responses \
-H "Authorization: Bearer hs_sk_..."공개 표면
문서 페이지:
https://www.humansurvey.co/docsOpenAPI:
https://www.humansurvey.co/api/openapi.jsonAI 인덱스:
https://www.humansurvey.co/llms.txt
기술 스택
구성 요소 | 기술 |
프레임워크 | Next.js (App Router) |
데이터베이스 | Neon (서버리스 Postgres) |
파서 | remark (unified 생태계) |
프론트엔드 | React + Tailwind CSS |
MCP 서버 | @modelcontextprotocol/sdk |
배포 | Vercel |
프로젝트 구조
├── apps/web/ # Next.js app (API + frontend)
├── packages/parser/ # Markdown → Survey JSON parser
├── packages/mcp-server/ # MCP server for Claude Code
└── docs/ # Architecture docs기여하기
PR을 열기 전에 CONTRIBUTING.md를 읽어보세요. 가장 중요한 규칙은 범위 규율입니다. 새로운 UI 변형, 분석 대시보드 및 인간 운영자 기능은 일반적으로 범위를 벗어납니다.
개발
pnpm install
pnpm dev # Start Next.js dev server
pnpm --filter @mts/parser test
pnpm build # Build all packages라이선스
MIT
Available Tools
5 toolsclose_surveyClose SurveyA
Permanently close a survey so it no longer accepts new responses. Use this when you have enough responses or the data collection window has passed. Returns the final response count. Closing is irreversible via MCP — use PATCH /api/surveys/{id} to re-open.
Inputs: survey_id (required).
create_keyCreate API KeyA
Create a new HumanSurvey API key. Call this before any other tool if HUMANSURVEY_API_KEY is not set. Returns a key — store it as HUMANSURVEY_API_KEY in your MCP config. The key cannot be retrieved again after creation.
Inputs: name, email, wallet_address.
create_surveyCreate SurveyA
Use this when an agent task involves collecting structured feedback or data from a group of people. Common cases: post-event attendee feedback, product satisfaction after a launch, team health checks, customer ratings after support resolution. The schema parameter is fully typed — follow the field types rather than guessing. Returns a survey_url to share with respondents and a survey_id to pass to get_results later. The survey accepts responses immediately and stays open until you close it or it expires. Embedding: append "?embed=1" to the returned survey_url to render inside an on any host site (onboarding/lead-capture flows). The embedded form posts events to window.parent with source: "humansurvey" — type "loaded", "resize" (with height), and "submitted" (with responseId and answers). See https://www.humansurvey.co/llms.txt for the full embed contract.
Inputs: schema (required), max_responses, expires_at, webhook_url.
get_resultsGet ResultsA
Retrieve aggregated results for a survey. Shows survey status (open/closed), total response count, and per-question results: choice tallies with percentages, scale mean/median/distribution, and recent text responses. If the survey is still open, call again later to check for new responses — the output will tell you. Use close_survey when you have enough responses.
Inputs: survey_id (required).
list_surveysList SurveysA
List all surveys created with the current API key, ordered newest first. Use this to find a survey_id you need for get_results or close_survey, or to check which surveys are still open.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool has a distinct, non-overlapping purpose: creating API keys, creating surveys, listing surveys, retrieving results, and closing surveys. No ambiguity.
All tool names follow a consistent verb_noun pattern in snake_case (create_key, create_survey, list_surveys, get_results, close_survey), making them predictable and easy to distinguish.
With 5 tools, the server is well-scoped for managing surveys. Each tool serves a necessary function without unnecessary bloat, fitting within the ideal range of 3-15 tools.
Covers core survey lifecycle (create, list, results, close) but lacks update and delete operations. While re-opening is possible via API, it's not exposed as a tool, creating a notable gap.
Maintenance
Related MCP Connectors
Create forms, share the link and read responses as JSON or CSV from your AI agent.
Create surveys, feedback and classification campaigns. Collect human answers and export results.
AI-native survey & form builder. Manage surveys, responses, analytics, and webhooks.
Ask people questions, get approvals and keep team decisions, from any AI agent.
Related MCP Servers
- AlicenseBqualityDmaintenanceCollects user feedback with text and image support through an Electron app, allowing AI tools to gather and process user input with customizable prompts and multiple response options.19 npm2Apache 2.0
- AlicenseAqualityCmaintenanceEnables AI agents to recruit real humans for evaluation tasks like surveys, A/B tests, and ratings on text, images, audio, and video, returning aggregated results directly into the conversation.137MIT
- AlicenseAqualityBmaintenanceFeedback ingestion for AI agents. Record your screen and talk; your agent does the rest — files the bugs, writes the spec, builds the backlog.997 PyPI35MIT
- AlicenseAqualityCmaintenanceReal human judgment as agent tools -- an AI agent can ask a question and get back a structured, schema-validated JSON answer from a real quality-scored human. 16 response types (yes/no, ratings, rankings, A/B tests, sentiment, image/video/audio review, voice/video/photo capture). Fully programmatic signup with a $5 free trial credit, no card required.747 npmMIT