Bilibili Video Research
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Your Gemini API key. | |
| STEPFUN_API_KEY | No | Your StepFun API key. | |
| STEPFUN_BASE_URL | No | The StepFun base URL, e.g. 'https://api.stepfun.com/v1' or 'https://api.stepfun.com/step_plan/v1'. | |
| DOTENV_CONFIG_PATH | No | Path to the .env file containing provider keys and configuration. | |
| CODEX_VIDEO_PROVIDER | No | The video provider to use. Set to 'stepfun' (default) or 'gemini'. | stepfun |
| BILIBILI_COOKIES_FILE | No | Absolute path to a Netscape-format cookies.txt for a logged-in Bilibili session. | |
| BILIBILI_COOKIES_FROM_BROWSER | No | Optional legacy setting: browser name to read cookies from ('edge', 'chrome', 'firefox', 'brave'). |
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 | Creates an audio-free copy of a local video and sends it to the configured video-analysis provider for visual research. Visible interfaces, code, charts, labels, and subtitles remain usable visual evidence. |
| inspect_video_windowA | Extracts an audio-free temporary clip for the requested source-video time window, then sends that clip to the configured video-analysis provider for visual-only analysis. Temporary media and remote uploads are removed after the answer. |
| analyze_bilibili_videoA | Resolves a public Bilibili URL, always returns public metadata and an explicit community-context status, and optionally samples 20 most-liked root comments while displaying only 3 hot comments plus up to 2 distinct high-signal comments. Supports language-only, visual-only, and multimodal research. |
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 3 tools
The three tools are mostly distinct: one handles public Bilibili URLs with community context, one handles local video files for visual analysis, and one handles specific time windows of local videos. However, 'analyze_video' and 'inspect_video_window' could be confused since both analyze local videos visually, though the window variant is time-specific.
Two tools use the 'analyze_*' verb-noun pattern, and one uses 'inspect_*', which is a similar verb. The naming is consistent in structure but the verb varies slightly. All use snake_case and are descriptive.
With only 3 tools, the server feels slightly thin for a video analysis domain. However, each tool covers a distinct use case, so the count is borderline and acceptable for a focused purpose.
The tools cover public URL analysis, full local video analysis, and windowed local video analysis, but lack features like metadata extraction for local videos, audio analysis, or comparison between videos. There are notable gaps such as no tool for local video metadata or audio transcription.