Filestash
A modular, extensible file manager with robust API and LLM Model Context Protocol (MCP) integration.
Key Features
Use Cases
README
Key Features
- Sleek, Speedy, Snappy, works great on Desktop and Mobile
- Extensible / Customisable / Hackable via a rich ecosystem of plugins and a Workflow engine to enable automation
- Shared Links which you can mount locally as network drives
- Manage your files not only from your browser but also via SFTP and S3 through third party tools
- Builtin Music, Video, Image viewers with optional transcoding and Chromecast support
- API and LLM integration via MCP
- Themes replicating the UX of dropbox, gdrive, github, ibm, onedrive, and more
- ... and much much much more
Documentation
Vision & Philosophy
Our goal is simple: to build the best file management platform ever made. Period. But "best" means different things to different people, and making Filestash modular is the only sane model to accomplish that. Anything that isn't a fundamental truth of the universe and might spark a debate belongs in a plugin.
This modularity is made possible by the magic of programming interfaces. For example, if you want a Dropbox-like frontend for FTP, you will find out the FTP plugin simply implements this interface:
type IBackend interface {
Ls(path string) ([]os.FileInfo, error) // list files in a folder
Cat(path string) (io.ReadCloser, error) // download a file
Mkdir(path string) error // create a folder
Rm(path string) error // remove something
Mv(from string, to string) error // rename something
Save(path string, file io.Reader) error // save a file
Touch(path string) error // create a file
// I have omitted 2 other methods, a first one to enable connections reuse and
// another one to declare what should the login form be like.
}
There are interfaces you can implement for every key component of Filestash: from storage, to authentication, authorisation, custom apps, search, thumbnailing, frontend patches, middleware, endpoint creation and a few others.
To see what's currently installed in your instance, head over to /about. The inventory of plugins is documented here.
Roadmap
There are 2 major pieces of work currently underway:
Support
- Commercial Users → support contract
- For individuals → #filestash on IRC (libera.chat).
Want to help us sprinkle some toppings on our noodle cups?
- Bitcoin:
3LX5KGmSmHDj5EuXrmUvcg77EJxCxmdsgW - Open Collective
Credits
Filestash stands on the shoulder of: contributors, folks developing awesome libraries, a whole bunch of C stuff (the C standard library, libjpeg, libpng, libgif, libraw and many more), fontawesome, material, Browser stack to let us test on real devices, and the many guys from Nebraska and elsewhere who have been thanklessly maintaining the critical pieces that Filestash sits on top:
Star History
Repository Owner
User
Repository Details
Programming Languages
Tags
Topics
Join Our Newsletter
Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.
Related MCPs
Discover similar Model Context Protocol servers
Zettelkasten MCP Server
A Zettelkasten-based knowledge management system implementing the Model Context Protocol.
Zettelkasten MCP Server provides an implementation of the Zettelkasten note-taking methodology, enriched with bidirectional linking, semantic relationships, and categorization of notes. It enables creation, exploration, and synthesis of atomic knowledge using MCP for AI-assisted workflows. The system integrates with clients such as Claude and supports markdown, advanced search, and a structured prompt framework for large language models. The dual storage architecture and synchronous operation model ensure flexibility and reliability for managing personal or collaborative knowledge bases.
- ⭐ 114
- MCP
- entanglr/zettelkasten-mcp
MarkItDown
Convert diverse files into Markdown for seamless LLM integration.
MarkItDown is a lightweight Python utility for converting a wide range of file types—including PDF, Office documents, images, audio, websites, and more—into structured Markdown optimized for language models and text analysis tools. It includes an implementation of the Model Context Protocol (MCP) to facilitate integration with LLM applications, such as Claude Desktop. MarkItDown supports context-aware document conversions, prioritizing preservation of hierarchy and meaningful content, and can be used via CLI or as a library.
- ⭐ 82,918
- MCP
- microsoft/markitdown
VideoDB Agent Toolkit
AI Agent toolkit that exposes VideoDB context to LLMs with MCP support
VideoDB Agent Toolkit provides tools for exposing VideoDB context to large language models (LLMs) and agents, enabling integration with AI-driven IDEs and chat agents. It automates context generation, metadata management, and discoverability by offering structured context files like llms.txt and llms-full.txt, and standardized access via the Model Context Protocol (MCP). The toolkit ensures synchronization of SDK versions, comprehensive documentation, and best practices for seamless AI-powered workflows.
- ⭐ 43
- MCP
- video-db/agent-toolkit
Mifos MCP - Model Context Protocol (MCP)
Enabling AI agents to access and operate on financial data in the Mifos X ecosystem using Model Context Protocol.
Mifos MCP provides a Model Context Protocol (MCP) interface tailored for the Mifos X ecosystem, empowering AI agents to interact with financial data and perform operations within the platform. It offers a Java (Quarkus) implementation, with easy configurability via environment variables and native executable support. Developers can test and debug deployments with the MCP Inspector, and detailed instructions ensure smooth setup and integration. Comprehensive examples demonstrate practical banking and financial automation workflows.
- ⭐ 17
- MCP
- openMF/mcp-mifosx
Volatility MCP
AI-assisted memory forensics via standardized APIs and MCP clients
Volatility MCP integrates the Volatility 3 framework for memory image analysis with a FastAPI backend, exposing forensic plugins as RESTful APIs. Featuring Model Context Protocol (MCP) support, it enables seamless interaction with AI assistants like Claude Desktop for advanced memory forensics. The platform connects memory artifacts to AI or web applications, offering natural language driven analysis and automation. Designed for security analysts and forensic professionals, it supports key Volatility plugins such as pslist and netscan.
- ⭐ 36
- MCP
- Gaffx/volatility-mcp
Memory MCP
A Model Context Protocol server for managing LLM conversation memories with intelligent context window caching.
Memory MCP provides a Model Context Protocol (MCP) server for logging, retrieving, and managing memories from large language model (LLM) conversations. It offers features such as context window caching, relevance scoring, and tag-based context retrieval, leveraging MongoDB for persistent storage. The system is designed to efficiently archive, score, and summarize conversational context, supporting external orchestration and advanced memory management tools. This enables seamless handling of conversation history and dynamic context for enhanced LLM applications.
- ⭐ 10
- MCP
- JamesANZ/memory-mcp
Didn't find tool you were looking for?