# bibi-proxy

> bibi-proxy — spherica233-bibi-proxy. Use this tool when you need to summarize videos and audio through a single interface, or require a reliable proxy for BibiGPT API keys with features like round-robin rotation and auth-error retry. It solves problems related to media summarization, subtitle generation, and content organization, providing 32 MCP tools for tasks like Notion export and mind mapping. The bibi-proxy tool takes in video and audio inputs and outputs summarized content, subtitles, and other organized data through a proxy URL.

Canonical page: https://skillsregistry.net/skills/spherica233-bibi-proxy  
JSON: https://api.skillsregistry.net/v1/skills/spherica233-bibi-proxy

## Description

A local MCP proxy for BibiGPT that lets users summarize videos and audio through a single proxy URL, injecting BibiGPT API keys with round-robin rotation, auth-error retry, and hot-reload, exposing 32 MCP tools for summarization, subtitles, chapters, saved videos, notes, collections, channels, feeds, Notion export, mind maps, and more.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/d8hehgf0sk)
- **Repository:** <https://github.com/spherica233/bibi-proxy>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "spherica233-bibi-proxy"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/spherica233-bibi-proxy` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/spherica233-bibi-proxy/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt