Skip to main content
Glama
humansurvey-mcp

humansurvey-mcp

by sunsiyuan

HumanSurvey

Website: humansurvey.co · Dokumentation: humansurvey.co/docs · FAQ: humansurvey.co/faq

human-survey MCP server

Infrastruktur zur Feedback-Sammlung für KI-Agenten.

HumanSurvey ermöglicht es einem Agenten, der langfristige Aufgaben ausführt, strukturiertes Feedback von einer Gruppe von Personen einzuholen:

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 them

Was ist das?

HumanSurvey ist eine minimale API und ein MCP-Server für eine spezifische Aufgabe: Agenten sollen strukturiertes Feedback von Gruppen von Menschen sammeln und maschinenlesbare Ergebnisse zurückerhalten können.

Es ist konzipiert für:

  • KI-Agenten, die Event-Management, Produkteinführungen oder Community-Workflows steuern und eine Gruppe befragen müssen

  • Entwickler, die Agenten-Produkte bauen und ein leichtgewichtiges Grundelement zur Feedback-Sammlung benötigen

Es ist nicht konzipiert für:

  • Umfrage-Dashboards

  • visuelle Formular-Editoren

  • Vorlagen-Bibliotheken

  • E-Mail-Kampagnen

  • Analyse-/Reporting-Benutzeroberflächen

Related MCP server: Datapoint MCP

Funktionen

  • JSON-Schema-Eingabe — strukturiert, präzise und direkt maschinell generierbar

  • MCP-Server — Umfragen erstellen und Ergebnisse direkt aus Claude Code lesen

  • Minimale API-Oberfläche — authentifizierte Ersteller-Routen, öffentliche Einreichung durch Befragte

  • Vier semantische Fragetypen — choice, text, scale, matrix

  • Bedingte Logik — showIf in Markdown und JSON-Schema

  • Expliziter Lebenszyklus — Umfragen schließen, Ablaufdatum und maximale Antwortbegrenzungen

Produktprinzipien

  • Semantik vor Optik: HumanSurvey hat ein kleines Protokoll, keinen Zoo an UI-spezifischen Feldtypen.

  • KI-First I/O: Agenten schreiben die Umfrage und Agenten konsumieren die Ergebnisse; Menschen sind das Bindeglied.

  • Alles ist eine API: Ersteller-Funktionalität muss über authentifiziertes HTTP und MCP verfügbar sein.

  • Enger Fokus gewinnt: Wenn eine Funktion hauptsächlich menschlichen Umfrage-Betreibern dient, gehört sie wahrscheinlich nicht hierher.

Unterstützte Fragetypen

  • single_choice

  • multi_choice

  • text

  • scale

  • matrix

Markdown-Syntax

# 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 |

Skalenfragen:

**Q4. How severe is this issue?**

[scale 1-5 min-label="Low" max-label="Critical"]

Bedingte Logik:

**Q1. Did the deploy fail?**

- ☐ Yes
- ☐ No

**Q2. Which step failed?**

> show if: Q1 = "Yes"

> _______________________________________________

Schnellstart

Verwendung mit Claude Code

Fügen Sie dies zu Ihrer Claude Code-Konfiguration (~/.claude.json) hinzu:

{
  "mcpServers": {
    "survey": {
      "command": "npx",
      "args": ["-y", "humansurvey-mcp"],
      "env": {
        "HUMANSURVEY_API_KEY": "hs_sk_your_key_here"
      }
    }
  }
}

Dann in Claude Code:

> Create a post-event feedback survey with a 1-5 rating, open text, and a yes/no question

Verfügbare Tools:

  • create_key — API-Schlüssel selbst bereitstellen; keine manuelle Einrichtung erforderlich

  • create_survey — Erstellung aus JSON-Schema; optional max_responses, expires_at, webhook_url

  • get_results — aggregierte Ergebnisse + Rohantworten

  • list_surveys — Auflistung der Umfragen, die Ihrem Schlüssel gehören

  • close_survey — eine Umfrage sofort schließen

Verwendung der HTTP-API

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..."
  }'

Alle Felder sind optional. wallet_address verwendet das CAIP-10 Format — wird in Zukunft für agenteneigene Zahlungen verwendet.

Dann eine Umfrage erstellen:

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?" }
        ]
      }]
    }
  }'

Antwort:

{
  "survey_url": "/s/abc123",
  "question_count": 1
}

Ergebnisse lesen:

curl https://www.humansurvey.co/api/surveys/abc123/responses \
  -H "Authorization: Bearer hs_sk_..."

Öffentliche Schnittstellen

  • Dokumentationsseite: https://www.humansurvey.co/docs

  • OpenAPI: https://www.humansurvey.co/api/openapi.json

  • KI-Index: https://www.humansurvey.co/llms.txt

Tech-Stack

Komponente

Technologie

Framework

Next.js (App Router)

Datenbank

Neon (serverless Postgres)

Parser

remark (unified ecosystem)

Frontend

React + Tailwind CSS

MCP-Server

@modelcontextprotocol/sdk

Deployment

Vercel

Projektstruktur

├── apps/web/          # Next.js app (API + frontend)
├── packages/parser/   # Markdown → Survey JSON parser
├── packages/mcp-server/ # MCP server for Claude Code
└── docs/              # Architecture docs

Mitwirken

Lesen Sie CONTRIBUTING.md, bevor Sie einen PR öffnen. Die wichtigste Regel ist Disziplin beim Umfang: neue UI-Varianten, Analyse-Dashboards und Funktionen für menschliche Betreiber sind in der Regel außerhalb des Projektumfangs.

Entwicklung

pnpm install
pnpm dev              # Start Next.js dev server
pnpm --filter @mts/parser test
pnpm build            # Build all packages

Lizenz

MIT

Available Tools

5 tools
close_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

    A4.4/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a distinct, non-overlapping purpose: creating API keys, creating surveys, listing surveys, retrieving results, and closing surveys. No ambiguity.

    Naming Consistency5/5

    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.

    Tool Count5/5

    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.

    Completeness3/5

    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

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Collects 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.
      1
      9 npm
      2
      Apache 2.0
    • A
      license
      A
      quality
      C
      maintenance
      Enables 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.
      13
      7
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Real 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.
      7
      47 npm
      MIT