ROAST MCP App
Enables authenticated ROAST users to view their dashboard, profiles, photoshoots, and images via MCP tools.
README
ROAST MCP App
Skybridge MCP / ChatGPT app for authenticated ROAST users.
The app exposes a protected /mcp endpoint, maps the OAuth identity to a ROAST
user_firebase_id, and calls the existing ROAST backend with a server-side
backend bearer token. Tool inputs never accept user_firebase_id; user scope is
always derived from auth.
Current Tools
show_roast_dashboard: dashboard view with account summary, recent profiles, photoshoots, and images.list_my_profiles: recent profile reviews for the authenticated user.list_my_photoshoots: recent photoshoots for the authenticated user.list_my_images: recent visible images for the authenticated user.
Setup
Requires Node.js 24+.
npm install
cp .env.example .env
npm run dev
Skybridge runs the MCP endpoint at http://localhost:3000/mcp and DevTools at
http://localhost:3000.
Auth Modes
Production: Auth0
Use ROAST_MCP_AUTH_MODE=auth0.
The access token is verified against Auth0 JWKS, then mapped to ROAST in this order:
ROAST_USER_ID_CLAIM, defaulting tohttps://roast.dating/user_firebase_id.- Authenticated email lookup through
GET /users?email=....
Required Auth0 scopes default to openid profile email.
Local: Dev Token
Use ROAST_MCP_AUTH_MODE=dev with:
ROAST_MCP_DEV_TOKEN=dev-roast-token
ROAST_MCP_DEV_USER_FIREBASE_ID=<existing-roast-user-firebase-id>
Then connect with:
Authorization: Bearer dev-roast-token
Environment
See .env.example.
Important variables:
SERVER_URL: public Skybridge server URL.APP_DOMAIN: public domain for rendered views.ROAST_API_BASE_URL: ROAST backend API base URL.ROAST_API_BEARER_TOKEN: backend-to-backend token accepted by ROAST.AUTH0_DOMAIN: Auth0 tenant domain.AUTH0_AUDIENCE: Auth0 API audience used for MCP access tokens.
Verify
npm run build
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.