Docsie
About
Docsie MCP brings your documentation workflow directly into Claude. Create, edit, and publish docs without leaving your AI assistant. Convert videos into structured documentation instantly, run compliance analysis on text, audio, and video content, and use semantic search to find
Details
- Author
- LikaloLLC
- Downloads
- 285
- Categories
- Productivity, Other, Knowledge Base, Security, AI, Search
Jump to
- Converts videos from YouTube, Loom, Vimeo, direct MP4, etc. into documentation
- Supports doc types: user guide, SOP, product docs, policy, blog
- Free tier for videos up to 5 minutes; longer videos require a Docsie AI credits account
- Provides three MCP tools: analyze_video, check_job_status, list_doc_types
- Uses OAuth2 Authorization Code + PKCE for secure authentication
- Deployed via Docker and Kubernetes with automated CI/CD via GitHub Actions
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
DocsieCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install locally via pip install -e . after cloning the repository, then run with uvicorn app.main:app --reload --port 8000. Configure environment variables in .env including a Dokuta API key. In production, deploy on Kubernetes using the provided Docker images and Helm chart. Claude users access the server via the Anthropic Connectors Directory at https://mcp.docsie.io/mcp and authenticate through Docsie's OAuth provider.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"docsie": {
"docsie": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://app.docsie.io/mcp"
],
"env": {
"API_KEY": "YOUR_API_KEY"
}
}
}
}
}McpServers
{
"docsie": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://app.docsie.io/mcp"
],
"env": {
"API_KEY": "YOUR_API_KEY"
}
}
}Docsie Video-to-Docs MCP Server
Remote MCP server for Anthropic's Connectors Directory. Converts videos into structured documentation using Dokuta AI.
What It Does
Users on Claude can:
1. Submit a video URL (YouTube, Loom, Vimeo, direct MP4, etc.)
2. Choose a doc type (user guide, SOP, product docs, policy, blog)
3. Get structured markdown documentation back
Free tier: Videos up to 5 minutes are processed free. Longer videos require a Docsie account with AI credits.
Architecture
Claude → POST https://mcp.docsie.io/mcp (Bearer token)
│
├─→ Docsie /o2/ (OAuth2 token validation)
├─→ Dokuta API (video analysis)
└─→ Docsie /api/internal/mcp/ (credit deduction)
- Transport: Streamable HTTP (MCP spec)
- Auth: OAuth2 Authorization Code + PKCE via Docsie's /o2/ provider
- Runtime: Python 3.12 + FastMCP + Starlette + uvicorn
MCP Tools
| Tool | Description |
|------|-------------|
| analyze_video | Submit a video URL for documentation generation |
| check_job_status | Poll for progress and retrieve completed results |
| list_doc_types | List available doc types and quality tiers |
Local Development
```bash
cd mcp-server
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
