Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@FrancoLabs MCP Server create a study for the new onboarding experience"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Connect AI assistants to FrancoLabs — a UX research platform — over the Model Context Protocol. Let Claude, ChatGPT and other MCP clients create and manage studies, browse templates, read participant responses and analytics, run AI-grounded analysis, and turn insights into product opportunities on your behalf.
Endpoint: https://francolabs.vercel.app/mcp
Transport: Streamable HTTP (MCP protocol 2025-06-18)
Auth: OAuth 2.1 (Dynamic Client Registration + PKCE) or Personal Access Token
Registry: io.github.glauberfrancodesign/francolabs
Settings → Connectors → Add custom connector → URL:
https://francolabs.vercel.app/mcpComplete the OAuth consent screen — you choose exactly which scopes to grant and can toggle read-only access.
Enable Developer Mode, then Settings → Connectors → Add → same URL. Authenticate via the OAuth flow.
Generate a Personal Access Token in Settings → Integrations, then:
claude mcp add --transport http francolabs \
"https://francolabs.vercel.app/mcp" \
--header "Authorization: Bearer <your-token>"Related MCP server: AI Survey Creator MCP Server
Tool | Scope | Description |
|
| List question/block types and their settings |
|
| List study templates, optionally by category |
|
| List the workspaces (teams) you belong to and your role in each |
|
| List your projects |
|
| Get a single project by id |
|
| Create a new project (optionally in a specific workspace) |
|
| List studies (filter by status/project) |
|
| Get a full study with blocks and settings |
|
| Create a study (auto-scaffolds welcome + thank-you) |
|
| Update title, blocks, settings or project |
|
| Launch / pause / resume / complete a study |
|
| Permanently delete a study and its responses |
|
| List participant responses (most recent first) |
|
| Aggregated KPIs: NPS, completion, distributions |
|
| Deterministic, PII-free statistical digest of a study's results |
|
| Run/refresh the full AI analysis (digest + grounded synthesis) |
|
| Ask a natural-language question, grounded in the study's analysis |
|
| List curated insight cards for a study |
|
| Create or update a curated insight card |
|
| Turn a research objective into a typed study skeleton |
|
| Review a study's questionnaire for survey-design issues |
|
| List product opportunities distilled from a study's insights |
|
| Distill insights into decision-ready product opportunities |
create_project and create_study write into a workspace — pass workspaceId
(see list_workspaces), or omit it to use your oldest workspace by default.
Two resources are also exposed: francolabs://templates and
francolabs://question-types.
templates:read · projects:read · projects:write · studies:read ·
studies:write · responses:read
Tools you didn't grant are hidden from tools/list. A read-only grant blocks
every write tool server-side, regardless of scopes.
Tokens are stored only as SHA-256 hashes — never in plaintext.
Each request mints a short-lived (5 min) JWT so all data access runs under per-user row-level security; the service role is used only for the token lookup.
Access is revocable anytime from Settings → Integrations.
OAuth follows RFC 9728 (protected-resource discovery), RFC 8414 (AS metadata), RFC 7591 (dynamic client registration) and PKCE S256.
This repository mirrors the server's source for transparency. The server runs as
a Supabase Edge Function (src/mcp, src/mcp-oauth, src/_shared).
© FrancoLabs. All rights reserved.
This server cannot be deployed
Run user research from any AI tool. Create studies, recruit participants, query insights.
AI-moderated research platform: create and launch studies and query interview results.
AI-powered user research for everyone
Create and edit surveys, read responses, and reply to users — from your AI assistant.
