This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Separate MCP + widget integration service for the FrameForge product. The public SaaS remains https://frameforger.com.
ChatGPT -> https://chatgpt.frameforger.com/mcp -> this integration service -> FrameForge backend -> FrameForger.com
The service is intentionally separate from the main FrameForge web app. It does not contain FrameForge generation logic; it exposes ChatGPT-safe MCP tools and forwards authenticated requests to the existing backend.
Related MCP server: YouTube MCP Server
generate_image -> FrameForge generateImage
generate_video -> FrameForge generateVideo
generate_scene -> FrameForge generateScene
open_frameforge -> opens the full FrameForge experience at FrameForger.com
All generation tools are marked as mutating, non-destructive, open-world operations. open_frameforge is read-only and idempotent.
Public launch is configured for OAuth 2.1 resource-server behavior.
The service exposes:
GET /.well-known/oauth-protected-resource
per-tool OAuth securitySchemes
mcp/www_authenticate challenges for unauthenticated tool calls
JWT signature, issuer, audience, expiry, and scope verification when OAUTH_ISSUER and OAUTH_JWKS_URL are configured
Use an established OAuth identity provider that supports the MCP authorization requirements and PKCE. Do not launch publicly with ALLOW_UNVERIFIED_BEARER=true.
The preferred backend mode is FRAMEFORGE_BACKEND_AUTH_MODE=forward, which forwards the linked user's bearer token to the FrameForge backend. This only works when the FrameForge backend recognizes tokens from the same issuer. If a separate identity provider is used, add a trusted server-side account-mapping gateway before enabling production generation.
Copy .env.example into your hosting provider's secret/environment settings.
Required for production:
MCP_PUBLIC_ORIGIN=https://chatgpt.frameforger.com
FRAMEFORGE_API_BASE=<authenticated FrameForge gateway/base URL>
OAUTH_ISSUER=<authorization server issuer>
OAUTH_JWKS_URL=<authorization server JWKS URL>
OAUTH_AUDIENCE=https://chatgpt.frameforger.com
npm install
npm startHealth endpoint:
curl http://localhost:8787/healthzMCP endpoint:
http://localhost:8787/mcpFor local ChatGPT testing, expose the server over a public HTTPS tunnel and add the tunneled /mcp URL in ChatGPT Developer Mode.
A Dockerfile and render.yaml are included. A suitable production deployment should:
run Node 20+ behind HTTPS;
map chatgpt.frameforger.com to the service;
keep OAuth and backend credentials in the hosting provider's secret store;
preserve streaming requests to /mcp;
route /healthz to health checks;
log request IDs, latency, backend status codes, and sanitized errors without logging bearer tokens.
submission.json contains the proposed listing name, short description, MCP URL, starter prompts, five positive review tests, and three negative review tests.
Before submitting publicly, verify that these URLs exist and accurately describe FrameForge data handling:
website: https://frameforger.com
privacy policy
terms
support/contact page
Also complete OpenAI developer/business identity verification in the same organization that submits the plugin/app.
Completed in this build:
Node syntax check (npm run check)
static MCP contract review
OAuth protected-resource metadata route added
tool-level OAuth security schemes added
JWT verification path added
Docker/Render deployment files added
submission manifest added
Not completed in this environment:
dependency installation (network install timed out)
live MCP Inspector run
end-to-end OAuth login
live FrameForge generation call
ChatGPT Developer Mode connection
Those require a reachable OAuth provider, production/test FrameForge backend URL, and deployed HTTPS endpoint.
This server cannot be deployed
Connect your AI assistant to Blender for 3D modeling, Geometry Nodes, materials, lighting, animation, rendering and export. Inspect real scenes and viewport images, refine the result and restore checkpoints. OAuth connects your chat to Blender Bridge Desktop on an online Windows 10/11 x64 computer running Blender 4.2+. The chat can run on another device. Requires an active Blender Bridge account; 7-day trial available. AI model access is separate.
Search bilingual image prompts, upload reference images, and generate and download images from your AI agent. OAuth sign-in; image generation uses paid subscription credits. Setup: https://framepond.com/en/agent?utm_source=agent_directory&utm_campaign=agent_launch
Generate images and video, run Spaces and build canvases from your agent. OAuth sign-in.
Use VoiceCheap’s media tools from your AI agent: transcribe audio, video and YouTube; create, translate and add subtitles to videos; generate YouTube chapters; create speech, design voices or clone voices with permission; generate images and thumbnails; translate and dub videos with optional lip sync; and publish completed projects to your connected channels. Manage project status, transcripts, glossaries and workspace settings through the tools you authorize. Available tools depend on your OAuth permissions and account access. Generation uses existing credits; purchases take place on the VoiceCheap website.
