Video MCP Server
by iceener
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Template setting for the host the server binds to. | |
| PORT | No | Template setting for the port the server listens on. | |
| NODE_ENV | No | Template setting for the Node environment (e.g. production, development). | |
| AUTH_MODE | No | Authentication mode. Production runs with AUTH_MODE=bearer, where every client sends the same shared token BEARER_TOKEN. Use AUTH_MODE=oauth to sign users in through an identity provider instead. | |
| LOG_LEVEL | No | Template setting controlling the server's log verbosity. | |
| BEARER_TOKEN | No | The shared token sent by every client as the header Authorization: Bearer <BEARER_TOKEN> when AUTH_MODE=bearer. The token only gets callers in; the server never forwards it. | |
| GEMINI_MODEL | No | The model that watches. It must support agentic video processing: gemini-4-argon, gemini-3.8-flash, gemini-3.6-flash or gemini-3.5-flash-lite. | gemini-3.8-flash |
| GEMINI_API_KEY | Yes | Required. A Gemini API key from Google AI Studio. Sent to Gemini only, in the x-goog-api-key header. Store it as a secret. | |
| GEMINI_API_URL | No | Change it only to point tests at a local mock. | https://generativelanguage.googleapis.com/v1beta |
| MCP_PUBLIC_URL | No | The deployed Worker's public URL, e.g. https://video-mcp.<subdomain>.workers.dev/mcp. This is the server URL clients connect to. | |
| MCP_LEGACY_MODE | No | Template setting that enables legacy protocol support. | |
| MCP_ALLOWED_HOSTS | No | Template setting listing the allowed hosts for incoming requests. | |
| MCP_MAX_REQUEST_BYTES | No | Template setting for the maximum size of an incoming request. | |
| MCP_ALLOWED_ORIGIN_HOSTNAMES | No | Template setting listing the allowed origin hostnames. Browser clients must use an origin listed here. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues