io.github.tlq5l/agentic-video
by tlq5l
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PYTHONPATH | No | Absolute path to the agentic-video repository, so the server can be started with `-m src.executor.mcp_server` from any folder. | |
| CLOUDFLARE_API_TOKEN | No | Cloudflare API token with Workers AI access, required only for the optional cloud tools `watch_for` and `label_sounds` (or use AGENTIC_VIDEO_CF_TOKEN_COMMAND instead). | |
| AGENTIC_VIDEO_EG2_DIR | No | Path to the EmbeddingGemma 2 Core ML model folder, enabling semantic (meaning-based) transcript search in `search_transcript` (macOS, optional). | |
| CLOUDFLARE_ACCOUNT_ID | No | Cloudflare account id, required only for the optional cloud tools `watch_for` and `label_sounds`. | |
| AGENTIC_VIDEO_CACHE_DIR | No | Directory for cached results. Defaults to ~/.cache/agentic-video. | |
| AGENTIC_VIDEO_EG2_PYTHON | No | Path to an interpreter with coremltools, tokenizers and numpy, used for EmbeddingGemma 2 semantic transcript search (optional, used together with AGENTIC_VIDEO_EG2_DIR). | |
| AGENTIC_VIDEO_INLINE_IMAGES | No | Set to 1 to include base64 images in tool results instead of only the JPEG file_path. By default images come back as files (AGENTIC_VIDEO_INLINE_IMAGES unset/0). | 0 |
| AGENTIC_VIDEO_CF_TOKEN_COMMAND | No | Command whose last printed line is the Cloudflare API token (for example `wrangler auth token`). Alternative to CLOUDFLARE_API_TOKEN for the optional cloud tools; runs at most once every 50 minutes. | |
| AGENTIC_VIDEO_WHISPER_CPP_MODEL | No | Path to the whisper.cpp model file (e.g. ggml-large-v3-turbo-q5_0.bin) if kept somewhere other than ~/.cache/whisper.cpp. When whisper.cpp is installed, `turbo` becomes the default transcribe model. |
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