Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
RNNOISE_REFNoPinned upstream commit for RNNoise.
COMFYUI_HOSTNoHostname of the optional ComfyUI backend. Typical value: host.docker.internal
COMFYUI_PORTNoPort of the optional ComfyUI backend. Default: 8188
CF_ACCESS_AUDNoCloudflare Access application audience tag.
MAX_UPLOAD_MBNoMaximum upload size in megabytes enforced while streaming files.
PIPER_ENABLEDNoWhether Piper TTS is enabled. Default: false
COMFYUI_SCHEMENoHTTP scheme for ComfyUI. Default: http
BLENDER_ENABLEDNoWhether to enable the optional Blender bridge. Default: false
PUBLIC_BASE_URLNoPublic base URL for authenticated HTTP(S) file streams, e.g. https://your-public-host.example. Enables get_cached_file_resource to return /files/{file_id} URLs.
RNNOISE_ENABLEDNoWhether RNNoise is enabled. Default: true
WHISPER_CPP_REFNoPinned upstream ref for whisper.cpp. Default: v1.8.6
CF_ACCESS_VERIFYNoWhether to verify Cloudflare Access JWT at the origin. Default: false
RNNOISE_MODEL_URLNoPublic URL for the RNNoise model.
VIDEO_MCP_VERSIONNoRelease version or commit SHA to run. Default: latest
WHISPER_MODEL_URLNoPublic URL for the Whisper model.
BLENDER_BRIDGE_URLNoURL of the authenticated Blender bridge. Default: http://host.docker.internal:9876
PIPER_PACKAGE_SPECNoPiper package specification. Default: piper-tts
RNNOISE_SOURCE_URLNoPublic source archive URL for RNNoise.
SILERO_VAD_ENABLEDNoWhether Silero VAD is enabled. Default: true
WHISPER_MODEL_NAMENoWhisper model name. Default: tiny-q5_1
COMFYUI_MODELS_PATHNoHost path to ComfyUI models directory for optional read-only filesystem discovery.
VIDEO_MCP_DATA_ROOTNoApplication runtime data root. Default: /data
WHISPER_CPP_ENABLEDNoWhether whisper.cpp is enabled. Default: true
BLENDER_BRIDGE_TOKENNoBearer token used by the MCP server to authenticate with the Blender bridge.
HYPERFRAMES_NPM_SPECNoHyperFrames npm package spec. Default: hyperframes@0.7.111
RNNOISE_MODEL_SHA256NoExpected SHA-256 of the RNNoise model.
SILERO_VAD_MODEL_URLNoPublic URL for the Silero VAD model.
WHISPER_MODEL_SHA256NoExpected SHA-256 of the Whisper model.
CF_ACCESS_TEAM_DOMAINNoCloudflare Access team domain, e.g. https://your-team.cloudflareaccess.com
RNNOISE_SOURCE_SHA256NoExpected SHA-256 of the RNNoise source archive.
WHISPER_CPP_BUILD_JOBSNoNumber of build jobs for whisper.cpp. Default: 2
HYPERFRAMES_SKIP_SKILLSNoWhether to skip HyperFrames skills. Default: 1
SILERO_VAD_MODEL_SHA256NoExpected SHA-256 of the Silero VAD model.
VIDEO_MCP_FORCE_REFRESHNoWhether to force refresh the release source. Default: false
CHATGPT_FILE_TIMEOUT_SECNoTimeout in seconds for ChatGPT attachment downloads. Default: 300
CLOUDFLARED_TUNNEL_TOKENNoToken used by the optional Cloudflare Tunnel sidecar.
COMFYUI_CUSTOM_NODES_PATHNoHost path to ComfyUI custom_nodes directory for optional read-only filesystem discovery.
REMOTE_IMPORT_TIMEOUT_SECNoTimeout in seconds for remote imports. Default: 120
BLENDER_BRIDGE_TIMEOUT_SECNoTimeout in seconds for Blender bridge operations. Default: 7200
CHATGPT_FILE_MAX_REDIRECTSNoMaximum number of redirects for ChatGPT attachment downloads. Default: 5
REMOTE_IMPORT_ALLOWED_HOSTSNoComma-separated list of allowed hosts for remote HTTPS imports.
REMOTE_IMPORT_MAX_REDIRECTSNoMaximum number of redirects for remote imports. Default: 5
WHISPER_MODEL_AUTO_DOWNLOADNoWhether to auto-download the Whisper model. Default: true
CHATGPT_FILE_MAX_BATCH_FILESNoMaximum number of files in a ChatGPT batch upload. Default: 20
VIDEO_MCP_CHECK_UPDATES_ON_STARTNoWhether to check for updates on start. Default: true

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

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/the-code-learner/MCP-video-gen'

If you have feedback or need assistance with the MCP directory API, please join our Discord server