Docsie

Name: Docsie
Author: LikaloLLC

@LikaloLLC

About Docsie

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

#documentation #productivity #ai #knowledge-base #video #compliance #search #writing

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "docsie": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.docsie.io/mcp"
      ],
      "env": {
        "API_KEY": "YOUR_API_KEY"
      }
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Docsie?

Docsie is a remote MCP (Model Context Protocol) server that converts videos into structured documentation using Dokuta AI. It integrates with Anthropic's Claude Connectors Directory, allowing users on Claude to submit a video URL and receive a markdown document such as a user guide, SOP, product docs, or blog post. It uses OAuth2 Authorization Code with PKCE for authentication and Streamable HTTP transport.

How to use Docsie?

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.

Key features of Docsie

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

Use cases of Docsie

Generate user guides from product demo videos
Create standard operating procedures (SOPs) from training recordings
Produce blog posts from video presentations or lectures
Convert meeting or webinar recordings into policy documents or meeting notes

FAQ from Docsie

What types of videos does Docsie support?

Docsie supports video URLs from YouTube, Loom, Vimeo, and direct MP4 files.

Is there a free tier?

Yes, videos up to 5 minutes are processed free. Longer videos require a Docsie account with AI credits.

How is authentication handled?

Docsie uses OAuth2 Authorization Code with PKCE. The server exposes a /.well-known/oauth-authorization-server endpoint for metadata and validates tokens via Docsie's /o2/ provider.

What transport protocol does Docsie use?

Docsie uses Streamable HTTP as specified by the MCP protocol.

How do I set up the Django backend for Docsie?

You need to configure an internal API key in Django settings, register an OAuth2 application as a public client with authorization code grant, and ensure internal endpoints for token validation and credit deduction are wired.

Comments

More Memory & Knowledge MCP servers

JupyterMCP - Jupyter Notebook Model Context Protocol Integration

jjsantos01

A Model Context Protocol (MCP) for Jupyter Notebook

130

RAG Documentation MCP Server

hannesrudolph

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

267