Sibyl Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Sibyl Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<div align="center">
<img src="assets/logo.png" alt="Sibyl" width="160" />
The oracle for Google's Gemini.
Where Pythia speaks for OpenAI, Sibyl speaks for Gemini. One MCP across the whole generative surface: text, image, video, speech, embeddings, and deep research. Built for personal use, shared openly, not productised.
<a href="https://www.buymeacoffee.com/hello_emrah"><img src="https://img.buymeacoffee.com/button-api/?text=Buy%20me%20a%20coffee&emoji=%E2%98%95&slug=hello_emrah&button_colour=2E7D74&font_colour=ffffff&coffee_colour=ffffff&outline_colour=ffffff&font_family=Inter" alt="Buy me a coffee" height="44" /></a>
</div>
Sibyl is a local Model Context Protocol server wrapping Google's Gemini generative API. It folds the old nano-banana (image) and gemini-deep-research servers into one coherent Gemini surface, and adds text, video, speech and embeddings, so an assistant reaches everything Gemini generates through a single tool set.
| Tool | What it does |
|---|---|
generate | Text, code, chat and reasoning with Gemini |
generate_image / edit_image | Generate or edit images (Nano Banana). Edit takes one or more inputs for compositing and iterative refinement |
generate_video / video_status | Generate video with Veo. Async: fire, then poll |
speak | Text to speech with Gemini TTS |
embed | Embedding vectors for one or more texts |
deep_research / research_get / research_followup | Fire an autonomous multi-step research task, poll it, and save a cited Markdown report; ask follow-ups without re-running |
git clone https://github.com/hello-emrah/sibyl-mcp.git
cd sibyl-mcp
npm install{
"mcpServers": {
"sibyl": {
"command": "node",
"args": ["/absolute/path/to/sibyl-mcp/index.js"],
"env": { "GEMINI_API_KEY": "your-key" }
}
}
}| Variable | Purpose |
|---|---|
GEMINI_API_KEY | Required. Your Gemini API key. |
GEMINI_DEEP_RESEARCH_API_KEY | Optional. A separate key for the research agent; falls back to GEMINI_API_KEY. |
GEMINI_TEXT_MODEL / GEMINI_IMAGE_MODEL / GEMINI_VIDEO_MODEL / GEMINI_TTS_MODEL / GEMINI_EMBED_MODEL | Optional model overrides; sensible current defaults otherwise. |
SIBYL_OUTPUT_DIR | Where research reports and embedding files land by default. |
MIT.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.