Epublys-MCP
Hosted Streamable HTTP MCP server (https://epublys.com/mcp) with 9 tools for EPUB/PDF manipulation: merge, split, compress, EPUB↔PDF conversion, metadata read/edit, validation with auto-fix, and AI cover generation. Free API key, no install. Listed on the official MCP registry as com.epublys/epublys.
README
Epublys MCP Server
Remote MCP server for EPUB and PDF ebook manipulation — merge, split, compress, convert, edit metadata, validate, and generate AI covers. Backed by epublys.com, running on Cloudflare Workers.
This is a hosted server (Streamable HTTP). There is nothing to install — this repository holds the public manifests, configuration examples, and documentation.
- Endpoint:
https://epublys.com/mcp(Streamable HTTP) - Auth: Bearer API key — free at https://epublys.com/account
- Server card: https://epublys.com/.well-known/mcp/server-card.json
- Full agent docs: https://epublys.com/llms-full.txt
- Registry:
com.epublys/epublyson the official MCP registry
Quickstart
- Sign up at https://epublys.com/account (free tier is permanent, not a trial) and create an API key (
epl_…— shown once). - Add to your MCP client config (
claude_desktop_config.json,cline_mcp_settings.json, etc.):
{
"mcpServers": {
"epublys": {
"url": "https://epublys.com/mcp",
"headers": { "Authorization": "Bearer epl_YOUR_KEY_HERE" }
}
}
}
Claude Code: claude mcp add --transport http epublys https://epublys.com/mcp --header "Authorization: Bearer epl_YOUR_KEY_HERE"
Tools
| Tool | Description |
|---|---|
merge_epub |
Merge multiple EPUB files into one |
split_epub |
Split an EPUB by chapter ranges |
compress_epub |
Compress an EPUB to reduce file size |
epub_to_pdf |
Convert EPUB to PDF |
pdf_to_epub |
Convert PDF to EPUB |
read_epub_metadata |
Read EPUB metadata |
edit_epub_metadata |
Edit EPUB metadata and cover |
validate_epub |
Validate EPUB structure (with optional auto-fix) |
generate_cover |
Generate an AI book cover from a description (Pro) |
Files are passed as base64-encoded strings in tool arguments and results.
Limits
| Free | Pro ($9/mo or $72/yr) | |
|---|---|---|
| File size | 10 MB (25 MB split_epub, 20 MB pdf_to_epub) |
100 MB |
| Merge | 10 files | 500 files |
| Rate | 15 req/min | 60 req/min |
| Output branding | Epublys colophon | none |
generate_cover |
— | 30/month |
Privacy
Files are processed in memory and never stored. There is no upload bucket, no retention, no content logging. Anonymous usage metrics only (tool name, status, sizes).
REST API
The same tools are available over plain REST with an OpenAPI spec — see https://epublys.com/for-ai-agents.
About this repository
The Epublys service itself is closed-source. This repository contains only the public MCP manifests (server.json, smithery.yaml) and documentation, and is the canonical public home for the com.epublys/epublys registry entry. Issues are welcome for MCP integration problems; for product support use https://epublys.com/about.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.