gemini-video-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_MODEL | No | Model to use | gemini-3.8-flash |
| GEMINI_API_KEY | Yes | Key from Google AI Studio | |
| GEMINI_TIMEOUT_MS | No | Request timeout in milliseconds | 600000 |
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| analyze_videoA | Analysiert ein oeffentliches YouTube-Video mit Google Gemini und beantwortet eine Frage dazu. Ohne "prompt" liefert das Tool eine vollstaendige Analyse mit Kapiteln, Zeitstempeln und visuellen Details. Bild und Ton werden gemeinsam ausgewertet. Die Antwort weist immer den Tokenverbrauch aus. Funktioniert nur mit oeffentlichen Videos (keine privaten oder nicht gelisteten). |
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 1 tool
With only one tool in the server, there is no possibility of confusion or overlap. The tool's purpose is clearly defined and distinct from any other hypothetical tool.
The single tool uses a clear snake_case verb_noun pattern ('analyze_video'), which is internally consistent. There are no other tools to deviate from the pattern.
The server has a narrow, focused purpose (analyzing YouTube videos with Gemini), so one tool is slightly under the typical 3-15 range but still appropriate and not excessive. It covers the core functionality without unnecessary fragmentation.
For the stated domain of video analysis, the tool is complete: it handles both open-ended analysis and specific questions, works with public videos, and reports token usage. There are no obvious missing operations or dead ends.