FrancoLabs MCP Server
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
Connect
Claude (claude.ai / Desktop)
Settings → Connectors → Add custom connector → URL:
https://francolabs.vercel.app/mcp
Complete the OAuth consent screen — you choose exactly which scopes to grant and
can toggle read-only access.
ChatGPT
Enable Developer Mode, then Settings → Connectors → Add → same URL.
Authenticate via the OAuth flow.
Claude Code / Cursor (manual token)
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>"
Tools
| Tool | Scope | Description |
|---|
list_question_types | templates:read | List question/block types and their settings |
list_templates | templates:read | List study templates, optionally by category |
list_workspaces | projects:read | List the workspaces (teams) you belong to and your role in each |
list_projects | projects:read | List your projects |
get_project | projects:read | Get a single project by id |
create_project | projects:write | Create a new project (optionally in a specific workspace) |
list_studies | studies:read | List studies (filter by status/project) |
get_study | studies:read | Get a full study with blocks and settings |
create_study | studies:write | Create a study (auto-scaffolds welcome + thank-you) |
update_study | studies:write | Update title, blocks, settings or project |
set_study_status | studies:write | Launch / pause / resume / complete a study |
delete_study | studies:write | Permanently delete a study and its responses |
list_responses | responses:read | List participant responses (most recent first) |
get_study_analytics | responses:read | Aggregated KPIs: NPS, completion, distributions |
get_study_digest | responses:read | Deterministic, PII-free statistical digest of a study's results |
run_universal_analysis | responses:read | Run/refresh the full AI analysis (digest + grounded synthesis) |
analysis_chat | responses:read | Ask a natural-language question, grounded in the study's analysis |
get_insights | responses:read | List curated insight cards for a study |
upsert_insight | studies:write | Create or update a curated insight card |
generate_study_from_objective | studies:read | Turn a research objective into a typed study skeleton |
review_study_quality | studies:read | Review a study's questionnaire for survey-design issues |
list_opportunities | responses:read | List product opportunities distilled from a study's insights |
create_opportunity_from_insights | studies:write | 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.
Scopes
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.
Security
- 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.
Source
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.
