Qualtrics MCP Server
A Model Context Protocol server that provides comprehensive control over the Qualtrics platform, enabling survey creation, question management, logic flows, distributions, contacts, and response exports through natural language.
README
Qualtrics MCP Server
A Model Context Protocol (MCP) server that gives Claude full control over the Qualtrics platform. Build surveys, manage questions, configure logic flows, distribute via email, handle contacts, export responses, and more — all through natural language.
What Can It Do?
53 tools across 8 domains covering the entire Qualtrics API surface:
| Domain | Tools | Capabilities |
|---|---|---|
| Surveys | 8 | Create, list, get, update, delete, activate, deactivate, estimate export size |
| Questions | 7 | Full CRUD + simplified helpers for multiple choice, text entry, and matrix/Likert |
| Blocks | 4 | Create, list, update, delete survey blocks |
| Survey Flow | 7 | Get/update flow, add embedded data, add web services, list fields, piped text reference |
| Responses | 7 | Export (with smart filtering + auto-save), get/create/update/delete individual responses |
| Contacts | 7 | Mailing lists CRUD, individual + bulk contact import, update, remove |
| Distributions | 5 | Email distributions, anonymous links, reminders, list, delete |
| Webhooks | 3 | Event subscriptions for survey lifecycle events |
| Users | 2 | List organization users, get user details |
Survey Management
list_surveys— List surveys with filtering and paginationget_survey— Get survey details, optionally with full definitioncreate_survey— Create a new surveyupdate_survey— Update name, status, expirationdelete_survey— Delete with name confirmation safety checkactivate_survey/deactivate_survey— Toggle collectionestimate_export_size— Preview data size before downloading
Question Management
list_questions— List all questions with types and previewsget_question— Get full question definitioncreate_question— Create with full Qualtrics spec (any type/selector)update_question— Modify text, choices, validationdelete_question— Remove a questionadd_multiple_choice_question— Simplified MC creation from a list of choice stringsadd_text_entry_question— Simplified TE creation (single/multi/essay)add_matrix_question— Simplified Likert/matrix with statements + scale points
Block Management
list_blocks/create_block/update_block/delete_block
Survey Flow & Logic
get_survey_flow— Full flow tree (blocks, randomizers, branches, embedded data, web services)update_survey_flow— Replace the entire flowadd_embedded_data— Inject embedded data fields into the flowadd_web_service— Call external APIs mid-survey with response-to-field mappinglist_embedded_data— List all declared embedded data fieldslist_web_services— List all web service elementspiped_text_reference— Look up${e://Field/...},${q://QID.../...}, etc. syntax
Response Export & Data
export_responses— Export all responses (auto-saves large files to Downloads)export_responses_filtered— Export with date ranges, completion filters, question selectioncheck_export_status— Poll an in-progress export jobget_response/create_response/update_response/delete_response
Contacts & Mailing Lists
list_mailing_lists/create_mailing_list/delete_mailing_listlist_contacts— Paginated contact listadd_contact/update_contact/remove_contactbulk_import_contacts— Import multiple contacts at once
Distributions
list_distributions/get_distribution/delete_distributioncreate_anonymous_link— Generate a shareable survey URLcreate_email_distribution— Send survey invitations to a mailing listcreate_reminder— Send follow-up reminders for existing distributions
Webhooks
list_webhooks/create_webhook/delete_webhook- Subscribe to events like
completedResponse.{surveyId},controlpanel.activateSurvey, etc.
Users
list_users/get_user
Server Control
set_read_only_mode— Toggle read-only mode at runtime (blocks all write/update/delete operations)
Setup
Prerequisites
- Node.js 22+
- Qualtrics API token with appropriate permissions
- Qualtrics data center ID
Installation
git clone https://github.com/yrvelez/qualtrics-mcp-server.git
cd qualtrics-mcp-server
pnpm install
Configure environment variables:
cp .env.example .env
# Edit .env with your Qualtrics credentials
Configuration
Set these in your .env file:
| Variable | Required | Default | Description |
|---|---|---|---|
QUALTRICS_API_TOKEN |
Yes | — | Your Qualtrics API token |
QUALTRICS_DATA_CENTER |
Yes | — | Data center ID (e.g., yul1) |
QUALTRICS_BASE_URL |
No | Auto-generated | Custom base URL override |
QUALTRICS_READ_ONLY |
No | false |
Block all write/delete operations (safe exploration mode) |
RATE_LIMITING_ENABLED |
No | true |
Enable/disable rate limiting |
RATE_LIMIT_RPM |
No | 50 |
Requests per minute |
REQUEST_TIMEOUT |
No | 30000 |
Request timeout in ms |
Read-Only Mode
Set QUALTRICS_READ_ONLY=true to block all write, update, and delete operations. This is useful for safely exploring surveys and exporting data without risk of accidental changes. You can also toggle this at runtime using the set_read_only_mode tool.
Claude Desktop Integration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"qualtrics": {
"command": "npx",
"args": ["tsx", "/path/to/qualtrics-mcp-server/src/index.ts"],
"env": {
"QUALTRICS_API_TOKEN": "your_api_token",
"QUALTRICS_DATA_CENTER": "your_data_center_id"
}
}
}
}
Usage Examples
Once configured, ask Claude things like:
Survey building:
- "Create a survey called 'Customer Satisfaction Q1 2026'"
- "Add a 5-point Likert matrix question measuring service quality"
- "Set up a randomizer that splits participants into two conditions"
- "Add embedded data fields for condition assignment and participant ID"
Data collection:
- "Create a mailing list and import these 50 contacts"
- "Send the survey to my research participants mailing list"
- "Generate an anonymous link for the pre-screen survey"
- "Send a reminder to everyone who hasn't responded yet"
Data export:
- "Export all complete responses from the last 30 days as CSV"
- "How many responses does my survey have? Estimate the export size"
- "Download responses for questions QID1-QID5 only"
Flow & logic:
- "Show me the current survey flow"
- "Add a web service call to my API that sets the stimulus condition"
- "What piped text syntax do I use to reference embedded data?"
Architecture
src/
config/settings.ts — Environment config with Zod validation
services/
qualtrics-client.ts — HTTP client with auth, rate limiting, read-only enforcement
survey-api.ts — Survey + question + block CRUD
flow-api.ts — Survey flow management
response-api.ts — Response export + individual response CRUD
contact-api.ts — Mailing list + contact management
distribution-api.ts — Email distributions + anonymous links
user-api.ts — Organization user lookups
webhook-api.ts — Event subscription management
tools/
survey-tools.ts — Survey MCP tool definitions
question-tools.ts — Question MCP tools (raw + simplified helpers)
block-tools.ts — Block MCP tools
flow-tools.ts — Flow, embedded data, web service, piped text tools
response-tools.ts — Export + individual response tools
contact-tools.ts — Mailing list + contact tools
distribution-tools.ts — Distribution tools
user-tools.ts — User tools
webhook-tools.ts — Webhook tools
_helpers.ts — Shared tool result helpers
index.ts — Tool registry
types/ — TypeScript type definitions
utils/ — File saving utilities
Development
pnpm start # Run the server
pnpm dev # Run with file watching
pnpm typecheck # Type check with tsgo
Troubleshooting
| Problem | Solution |
|---|---|
"Unexpected token 'Q'" |
Ensure no console.log statements interfere with MCP JSON protocol |
"Read-only file system" |
Use absolute paths or let auto-save write to Downloads |
| Large file timeouts | Use export_responses_filtered with date ranges and questionIds |
| Rate limit errors | Built-in rate limiting handles this automatically; reduce RATE_LIMIT_RPM if needed |
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.