Sibyl
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Required. Your Gemini API key. | |
| GEMINI_TTS_MODEL | No | Optional model override for text-to-speech. | |
| SIBYL_OUTPUT_DIR | No | Where research reports and embedding files land by default. | |
| GEMINI_TEXT_MODEL | No | Optional model override for text generation. | |
| GEMINI_EMBED_MODEL | No | Optional model override for embeddings. | |
| GEMINI_IMAGE_MODEL | No | Optional model override for image generation. | |
| GEMINI_VIDEO_MODEL | No | Optional model override for video generation. | |
| GEMINI_DEEP_RESEARCH_API_KEY | No | Optional. A separate key for the research agent; falls back to GEMINI_API_KEY. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generateA | Generate text with Gemini: prose, code, chat, reasoning. The core generative call. |
| generate_imageA | Generate an image from a text prompt with Gemini (Nano Banana). Saves to output_path. |
| edit_imageA | Edit or combine one or more input images with a natural-language instruction (style transfer, inpainting, compositing). Pass a prior output back in to keep refining. Saves to output_path. |
| generate_videoA | Generate a video from a text prompt with Veo. Async: returns an operation name, then poll video_status. Veo takes 1-3 minutes and is billed per second. |
| video_statusB | Poll a Veo generation by its operation name. When done, downloads the mp4 to output_path. |
| speakC | Text to speech with Gemini TTS. Saves a WAV to output_path. (Music generation rides with the Live API in a later version.) |
| embedA | Create embedding vectors for one or more texts with Gemini. Writes the vectors to a JSON file and returns the path and dimensions. |
| deep_researchA | Fire a Gemini Deep Research task asynchronously. Returns an interaction_id; poll research_get every 60s. Takes 5-20 minutes, costs roughly $2-5 per task. |
| research_getA | Poll a running research task. When complete, saves a cited Markdown report to output_dir and returns the path. Pass the same format/citation/tone used to start it. |
| research_followupA | Ask a follow-up on a completed research task without re-running it. Returns the answer inline, saves nothing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
Each tool targets a distinct modality or workflow stage: text, image, video, speech, embeddings, and research. The research trio (deep_research, research_get, research_followup) forms a clear lifecycle, and generate_image vs edit_image are clearly separated by creation vs modification.
Names are descriptive but inconsistent in pattern: some are verb-first (generate_image, edit_image), some object-first (video_status, research_get), and others are single verbs (speak, embed). This mixing prevents a predictable convention, though the names remain readable.
With 10 tools, the server is well-scoped for a multimodal AI toolkit covering text, image, video, speech, embeddings, and research. The count feels balanced and not bloated.
Core generation and editing are covered across all major modalities, plus embeddings and a full research workflow. Minor gaps exist, such as the absence of image/video understanding tools and music generation, but these are not essential for the primary purpose.