Verzeichnis
A c# backend that provides AI agents with secure, controlled access to the local file system.
claude mcp add --transport stdio stephanj79-verzeichnis-server-mcp dotnet run --project path/to/VerzeichnisServer.csproj \ --env PORT="Optional port for the MCP server" \ --env LOG_LEVEL="Information" \ --env ASPNETCORE_ENVIRONMENT="Development or Production"
How to use
Verzeichnis-Server-MCP is a C# backend that enables AI agents to interact with the local filesystem in a secure and controlled manner. It exposes a set of skills such as listing directories (directory_list), copying files (copy_file), moving/renaming files (move_file), deleting files (delete_file), reading text (read_text_file) and media files (read_media_file), writing text files (write_text_file), and creating or deleting directories (create_directory, delete_directory). The server adheres to the MCP protocol, allowing agents to request these actions and receive structured results, including file contents or directory listings. You can use it in workflows like N8N to automate file operations, content extraction, or media handling on the host system. To interact, authenticate as needed and invoke the appropriate skill with the required parameters (e.g., paths, content, or mime types).
How to install
Prerequisites:
- .NET SDK (6.0+ recommended)
- Basic familiarity with running .NET console applications
Installation steps:
# 1. Clone the repository
git clone https://github.com/example/Verzeichnis-Server-MCP.git
cd Verzeichnis-Server-MCP
# 2. Restore and build
dotnet restore
dotnet build -c Release
# 3. Run the server (example using the published project path in the MCP config)
dotnet run --project path/to/VerzeichnisServer.csproj
If you prefer to run via a container, you can create a Docker image from the published output and run the container, ensuring the necessary filesystem permissions are granted to the container.
Additional notes
Tips:
- Ensure the MCP server has the necessary filesystem permissions for the target paths. Restrict paths when running in shared or production environments to mitigate risk.
- If you encounter permission errors, adjust user privileges or run the server with elevated rights as appropriate for your environment.
- Use the read_media_file and read_text_file skills with explicit path validation to prevent unauthorized access.
- For recursive directory listings, ensure the client sets the recursive flag if supported by the MCP endpoint.
- Environment variables like PORT or ASPNETCORE_ENVIRONMENT can help with deployment configurations; adjust them according to your hosting setup.
Related MCP Servers
context-space
Ultimate Context Engineering Infrastructure, starting from MCPs and Integrations
dexto
A coding agent and general agent harness for building and orchestrating agentic applications.
aser
Aser is a lightweight, self-assembling AI Agent frame.
moling
MoLing is a computer-use and browser-use based MCP server. It is a locally deployed, dependency-free office AI assistant.
mcp-typescript-sdk
A TypeScript SDK for implementing Model Context Protocol (MCP) over MQTT, supporting both browser and Node.js environments.
mcp -js
MCP server that exposes YepCode processes as callable tools for AI platforms. Securely connect AI assistants to your YepCode workflows, APIs, and automations.