IMON Framer Chat MCP
Private remote MCP gateway connecting ChatGPT to one configured Framer project. Exposes read, controlled write, and separate publishing tools over /mcp, with authentication and environment-based security controls.
README
IMON Framer Chat MCP
Private remote MCP gateway for connecting ChatGPT to one configured Framer project. It exposes focused read tools, controlled write tools, and separate publishing tools over /mcp.
Architecture
ChatGPT / MCP client
-> HTTPS /mcp
-> framer-chat-mcp
-> framer-api
-> one server-configured Framer project
The server is tool-only. There is no widget UI in v1. The Framer project URL and API key are server-side configuration only; tool input cannot switch projects.
Security Model
- Production must use authentication.
MCP_AUTH_MODE=noneis rejected whenNODE_ENV=production. oauth-jwtvalidates JWT issuer, audience, expiry, and signature through JWKS.beareris available for private/dev deployments and MCP Inspector testing.- Writes require
FRAMER_WRITES_ENABLED=true. - Publishing and production deploy require
FRAMER_PUBLISH_ENABLED=true. - No tool publishes as a side effect of an edit.
- Framer content is untrusted data and never changes server configuration.
Local Setup
npm ci
cp .env.example .env.local
npm run typecheck
npm test
npm run build
npm run smoke:mcp
For local development without auth:
MCP_AUTH_MODE=none npm run dev
Health endpoints:
curl http://localhost:8787/healthz
curl http://localhost:8787/readyz
Environment Variables
Required for live Framer tools:
FRAMER_PROJECT_URL=
FRAMER_API_KEY=
EXPECTED_FRAMER_PROJECT_NAME=
Auth:
MCP_AUTH_MODE=none|bearer|oauth-jwt
MCP_ACCESS_TOKEN=
OAUTH_ISSUER=
OAUTH_AUDIENCE=
OAUTH_JWKS_URL=
ALLOWED_USER_EMAIL=
ALLOWED_SUBJECTS=
Controls:
FRAMER_WRITES_ENABLED=false
FRAMER_PUBLISH_ENABLED=false
Framer Credential Setup
From Framer documentation and framer-api README:
- Open the Framer project.
- Open settings, for example with Cmd+K and "open settings".
- Find the API Keys section.
- Create a Server API key.
- Store it only in Vercel or local ignored env, never in Git.
Commands
npm run lint
npm run typecheck
npm test
npm run build
npm run doctor
npm run smoke:mcp
npm run live:read
npm run security:scan
live:read requires Framer env vars and writes private output only under .local/.
Vercel Deploy
This repo includes api/index.ts and vercel.json for Node.js 24 Vercel Functions.
vercel link
vercel env add FRAMER_PROJECT_URL production
vercel env add FRAMER_API_KEY production
vercel env add MCP_AUTH_MODE production
vercel env add OAUTH_ISSUER production
vercel env add OAUTH_AUDIENCE production
vercel env add OAUTH_JWKS_URL production
vercel deploy --prod
If Framer credentials are not set, /healthz still works and Framer tools return CONFIGURATION_ERROR.
ChatGPT Setup
Use the deployed MCP URL:
https://<deployment>/mcp
Smoke prompts:
Use IMON Framer and show me the current project information.
List all pages in the connected Framer project. Do not make changes.
Inspect the homepage structure and summarize its top-level sections. Do not modify anything.
List the CMS collections and their schemas.
Show whether there are unpublished changes.
Limitations
- No public App Directory submission is prepared in v1.
- OAuth provider setup is code-supported but provider tenant/app creation is external.
- Live Framer tests require a real Framer Server API key.
- Broad canvas edits use official
framer.agent.applyChangesDSL behindFRAMER_WRITES_ENABLED; they are not arbitrary JavaScript execution.
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.